
from pprint import pprint
import numpy as np
import pandas as pd

# Libraries to help with data visualization
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from IPython.core.display import display

#preprocessing for model
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler, Normalizer
import sklearn.metrics as metrics
from sklearn.model_selection import train_test_split

#tensorflow libraries
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.metrics import Precision, Recall, BinaryAccuracy

INFO:tensorflow:Enabling eager execution
INFO:tensorflow:Enabling v2 tensorshape
INFO:tensorflow:Enabling resource variables
INFO:tensorflow:Enabling tensor equality
INFO:tensorflow:Enabling control flow v2


# Utility Functions

#Function to make a summary df to aid EDA
def make_summary_cols(df, cat_threshold=20):
    '''Create a df to summarise the data df based on dtypes, nulls, numeric or not, categorical or not

    df: data threshold
    cat_threshold: number of unique types below which assume categorical

    returns:
    summary_cols: df of summary
    d: dict of column names where keys are numeric_cols, categorical_cols and non_numeric_cols where
    values against the keys contain corresponding column names
    '''
    types = df.dtypes
    types.name = 'col_types'

    nuniques = data.nunique()
    nuniques.name = 'n_uniques'

    nulls = df.isnull().sum()
    nulls.name = 'nulls'

    summary_cols = pd.merge(left=pd.merge(left=nuniques, right=types, left_index=True, right_index=True), right=nulls,\
                            left_index=True, right_index=True).sort_values(by='col_types')
    summary_cols['isnumeric_column'] = summary_cols['col_types'].apply(lambda x: False if x=='object' else True)

    summary_cols['probably_categorical'] = summary_cols['n_uniques'].apply(lambda x: True if x <=cat_threshold \
        else False)

    d = {
        'numeric_cols': list(summary_cols[summary_cols.isnumeric_column==True].index),
        'categorical_cols': list(summary_cols[summary_cols.probably_categorical==True].index),
        'non_numeric_cols': list(summary_cols[summary_cols.isnumeric_column==False].index)
    }

    return summary_cols, d

#Plot histogram and boxplot together
def histogram_boxplot(feature, figsize=(15,10), bins = None):
    """ Boxplot and histogram combined
    feature: 1-d feature array
    figsize: size of fig (default (9,8))
    bins: number of bins (default None / auto)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(nrows = 2, # Number of rows of the subplot grid= 2
                                           sharex = True, # x-axis will be shared among all subplots
                                           gridspec_kw = {"height_ratios": (.25, .75)}, 
                                           figsize = figsize 
                                           ) # creating the 2 subplots
    sns.boxplot(x=feature, ax=ax_box2, showmeans=True, color='violet') # boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(x=feature, kde=True, ax=ax_hist2, bins=bins,palette="winter") if bins else sns.histplot(x=feature, kde=True, ax=ax_hist2) # For histogram
    ax_hist2.axvline(np.mean(feature), color='green', linestyle='--') # Add mean to the histogram
    ax_hist2.axvline(np.median(feature), color='black', linestyle='-') # Add median to the histogram

#Plot confusion matrix
def make_confusion_matrix(model, y_actual, y_predict=None, labels=[1, 0], cmap='Blues'):
    '''
    model : classifier to predict values of X
    y_actual : ground truth  
    
    '''
    if y_predict is None:
        y_predict = model.predict(X_test)

    cm=metrics.confusion_matrix(y_actual, y_predict, labels=[0, 1])
    df_cm = pd.DataFrame(cm, index = [i for i in ["Actual - No","Actual - Yes"]],
                  columns = [i for i in ['Predicted - No','Predicted - Yes']])
    group_counts = ["{0:0.0f}".format(value) for value in
                cm.flatten()]
    group_percentages = ["{0:.2%}".format(value) for value in
                         cm.flatten()/np.sum(cm)]
    labels = [f"{v1}\n{v2}" for v1, v2 in
              zip(group_counts,group_percentages)]
    labels = np.asarray(labels).reshape(2,2)
    plt.figure(figsize = (10,7))
    sns.heatmap(df_cm, annot=labels,fmt='', cmap=cmap)
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    
# Function to add data labels to bar plots
def show_values_on_bars(axs):
    def _show_on_single_plot(ax):        
        for p in ax.patches:
            _x = p.get_x() + p.get_width() / 2
            _y = p.get_y() + p.get_height()
            value = '{:.2f}'.format(p.get_height())
            ax.text(_x, _y, value, ha="center") 

    if isinstance(axs, np.ndarray):
        for idx, ax in np.ndenumerate(axs):
            _show_on_single_plot(ax)
    else:
        _show_on_single_plot(axs)


data = pd.read_csv('bank.csv')


data.head()


data.shape

(10000, 14)


data.isnull().sum()

RowNumber          0
CustomerId         0
Surname            0
CreditScore        0
Geography          0
Gender             0
Age                0
Tenure             0
Balance            0
NumOfProducts      0
HasCrCard          0
IsActiveMember     0
EstimatedSalary    0
Exited             0
dtype: int64


data.nunique()

RowNumber          10000
CustomerId         10000
Surname             2932
CreditScore          460
Geography              3
Gender                 2
Age                   70
Tenure                11
Balance             6382
NumOfProducts          4
HasCrCard              2
IsActiveMember         2
EstimatedSalary     9999
Exited                 2
dtype: int64


data.dtypes

RowNumber            int64
CustomerId           int64
Surname             object
CreditScore          int64
Geography           object
Gender              object
Age                  int64
Tenure               int64
Balance            float64
NumOfProducts        int64
HasCrCard            int64
IsActiveMember       int64
EstimatedSalary    float64
Exited               int64
dtype: object


data.describe().T


data.describe(include=['object']).T


# Creating new df dropping unnecessary columns
working_df = data.drop(['RowNumber','CustomerId','Surname'], axis=1)


# create lists of columns by type
summary_df, d = make_summary_cols(working_df)

numeric_cols = d['numeric_cols']
categorical_cols = d['categorical_cols']
non_numeric_cols = d['non_numeric_cols']

numeric_cols.sort()
categorical_cols.sort()
non_numeric_cols.sort()

summary_df


print(f'numeric cols are: \n {numeric_cols}\n')
print(f'categorical cols (defined as <= 20 uniques) are: \n {categorical_cols}\n')
print(f'non numeric cols are: \n {non_numeric_cols}')

numeric cols are: 
 ['Age', 'Balance', 'CreditScore', 'EstimatedSalary', 'Exited', 'HasCrCard', 'IsActiveMember', 'NumOfProducts', 'Tenure']

categorical cols (defined as <= 20 uniques) are: 
 ['Exited', 'Gender', 'Geography', 'HasCrCard', 'IsActiveMember', 'NumOfProducts', 'Tenure']

non numeric cols are: 
 ['Gender', 'Geography']


histogram_boxplot(working_df.CreditScore)


px.box(working_df.CreditScore, orientation='h', height=200)


px.histogram(working_df.CreditScore)


working_df.CreditScore.describe()

count    10000.000000
mean       650.528800
std         96.653299
min        350.000000
25%        584.000000
50%        652.000000
75%        718.000000
max        850.000000
Name: CreditScore, dtype: float64


histogram_boxplot(working_df.Age)


px.box(working_df.Age, orientation='h', height=200)


print(f'No. of rows with age > 62: {working_df[working_df.Age>62].count()[1]}')

No. of rows with age > 62: 359


working_df.Age.describe()

count    10000.000000
mean        38.921800
std         10.487806
min         18.000000
25%         32.000000
50%         37.000000
75%         44.000000
max         92.000000
Name: Age, dtype: float64


histogram_boxplot(working_df.EstimatedSalary)


px.box(working_df.EstimatedSalary,orientation='h',height=200)


working_df.EstimatedSalary.describe()

count     10000.000000
mean     100090.239881
std       57510.492818
min          11.580000
25%       51002.110000
50%      100193.915000
75%      149388.247500
max      199992.480000
Name: EstimatedSalary, dtype: float64


histogram_boxplot(working_df.Balance)


px.box(working_df.Balance, orientation='h', height=200)


#working_df[working_df.Balance == 0].count()
working_df.Balance.value_counts()

0.00         3617
105473.74       2
130170.82       2
72594.00        1
139723.90       1
             ... 
130306.49       1
92895.56        1
132005.77       1
166287.85       1
104001.38       1
Name: Balance, Length: 6382, dtype: int64


working_df.Balance.describe()

count     10000.000000
mean      76485.889288
std       62397.405202
min           0.000000
25%           0.000000
50%       97198.540000
75%      127644.240000
max      250898.090000
Name: Balance, dtype: float64


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Tenure)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.NumOfProducts)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.HasCrCard)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.IsActiveMember)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Exited)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Geography)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Gender)
show_values_on_bars(zz)


sns.pairplot(working_df,corner=True,diag_kind='kde')

<seaborn.axisgrid.PairGrid at 0x7fd1989856d0>


plt.figure(figsize=(15,15))
sns.heatmap(working_df.loc[:,numeric_cols].corr(), annot=True, fmt='.2f', cmap='coolwarm')

<AxesSubplot:>


working_df.groupby('Exited').mean()


working_df.groupby('Exited').median()


crosstabs = []
for i,col in enumerate(categorical_cols[1:]):
    crosstabs.append(pd.crosstab(working_df.Exited, working_df[col], normalize='columns'))
    display(crosstabs[i])


fig, axes = plt.subplots(6,1, figsize=(25,15))

for i,x in enumerate(crosstabs):
    zz=crosstabs[i].plot(kind='bar',ax=axes[i])
    show_values_on_bars(zz)


working_df[working_df.Balance==0].groupby('Exited').count().iloc[:,1]

Exited
0    3117
1     500
Name: Geography, dtype: int64


temp_df = working_df.copy()
temp_df['BalanceZero'] = temp_df.Balance.apply(lambda x: 1 if x ==0 else 0)

temp_df.groupby('BalanceZero').mean()
del(temp_df)


# Form X and y
X = working_df.drop('Exited', axis=1)
y = working_df.Exited

#Convert categorical non numeric to one hot encoding
X = pd.get_dummies(X, drop_first=True)

#Define random_state for all algorithms that use this
random_state = 314159

X

y

0       1
1       0
2       1
3       0
4       0
       ..
9995    0
9996    0
9997    1
9998    1
9999    0
Name: Exited, Length: 10000, dtype: int64


# defined class weights dictionary per keras tutorial
neg, pos = np.bincount(working_df['Exited'])
total = neg + pos
print('class weights:\n    Total: {}\n    Positive: {} ({:.2f}% of total)\n'.format(
    total, pos, 100 * pos / total))

class weights:
    Total: 10000
    Positive: 2037 (20.37% of total)


# define scaler
#https://stackoverflow.com/a/58850139 for ref on which scaler to use
scaler = RobustScaler(quantile_range=(25,75)) #using this as it retains shape of data distribution and also retains outliers 

#in any case RobustScaler yields better results than MinMax or Standard scalers


# Perform train test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, stratify=y, random_state=random_state)


X_test


# Checking that target split ratio maintained in train and test sets
print(f'% of +ve class in target in full dataset: {working_df[working_df.Exited==1].shape[0]/ working_df.shape[0]}')
print(f'% of +ve class in target in train: {y_train.value_counts()[1]/ len(y_train):0.4f}')
print(f'% of +ve class in target in test: {y_test.value_counts()[1]/ len(y_test):0.4f}')

% of +ve class in target in full dataset: 0.2037
% of +ve class in target in train: 0.2037
% of +ve class in target in test: 0.2037


# Scaling data
# To prevent test data leaking into train, we fit the scaler on train and then transform both train and test on that scaler

X_train = pd.DataFrame(scaler.fit_transform(X_train), columns=X_train.columns)
X_test = pd.DataFrame(scaler.transform(X_test), columns = X_test.columns)



print('Scaled X_train:')
display(X_train.describe().T)

print('\nScaled X_test:')
display(X_test.describe().T)

Scaled X_train:

Scaled X_test:


# Defining metrics - keras tutorial
# I retain these functions here to aid ready reference as needed to tune models
# Modified from source found at: https://www.tensorflow.org/tutorials/structured_data/imbalanced_data

colors = plt.rcParams['axes.prop_cycle'].by_key()['color']

THRESHOLD = 0.5 # threshold used to determine if output is 0 or 1 (since sigmoid outputs a continuous no between 0 and 1)

EPOCHS=100 # baseline epochs for model run

BATCH_SIZE=100 # baseline batchsize

#metrics for model to compute
METRICS = [
      keras.metrics.TruePositives(name='tp'),
      keras.metrics.FalsePositives(name='fp'),
      keras.metrics.TrueNegatives(name='tn'),
      keras.metrics.FalseNegatives(name='fn'), 
      keras.metrics.BinaryAccuracy(name='accuracy'),
      keras.metrics.Precision(name='precision'),
      keras.metrics.Recall(name='recall'),
      keras.metrics.AUC(name='auc'),
      keras.metrics.AUC(name='prc', curve='PR'), # precision-recall curve
]

#function to define and compile model
def make_model(metrics=METRICS, output_bias=None, dropout=False, learning_rate=1e-3, activation='relu'):
    if output_bias is not None:
        print('bias being set')
        output_bias = tf.keras.initializers.Constant(output_bias)
    
    model = keras.Sequential()
  
    model.add(keras.layers.Dense(16, activation=activation,input_shape=(X_train.shape[-1],)))
    
    if dropout==True:
        model.add(keras.layers.Dropout(0.5))
    
    model.add(keras.layers.Dense(1, activation='sigmoid', bias_initializer=output_bias))

    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate=learning_rate),
        loss=keras.losses.BinaryCrossentropy(),
        metrics=metrics)

    return model

#variant of above
def make_model2(metrics=METRICS, output_bias=None, dropout=False, learning_rate=1e-3):
    if output_bias is not None:
        print('bias being set')
        output_bias = tf.keras.initializers.Constant(output_bias)
    
    model = keras.Sequential()
  
    model.add(keras.layers.Dense(64, activation='relu',input_shape=(X_train.shape[-1],)))
    
    if dropout==True:
        model.add(keras.layers.Dropout(0.7))
    
    model.add(keras.layers.Dense(24, activation='relu', bias_initializer=output_bias))
    
    if dropout==True:
        model.add(keras.layers.Dropout(0.6))

    
    model.add(keras.layers.Dense(1, activation='sigmoid', bias_initializer=output_bias))

    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate=learning_rate),
        loss=keras.losses.BinaryCrossentropy(),
        metrics=metrics)

    return model

#function to plot model metrics (loss, accuracy, recall and precision)
def plot_metrics(history):
  metrics = ['loss', 'accuracy', 'precision', 'recall']
  for n, metric in enumerate(metrics):
    name = metric.replace("_"," ").capitalize()
    plt.subplot(2,2,n+1)
    plt.plot(history.epoch, history.history[metric], color=colors[0], label='Train')
    plt.plot(history.epoch, history.history['val_'+metric],
             color=colors[1], linestyle="--", label='Val')
    plt.xlabel('Epoch')
    plt.ylabel(name)
    if metric == 'loss':
      plt.ylim([0, plt.ylim()[1]])
    elif metric == 'auc':
      plt.ylim([0.8,1])
    else:
      plt.ylim([0,1])

    plt.legend()


%%time
model1 = make_model()
#start with 100 epochs
history1 = model1.fit(X_train, y_train, epochs=EPOCHS, batch_size=BATCH_SIZE, use_multiprocessing=True, validation_split=0.2)

Epoch 1/100
56/56 [==============================] - 3s 14ms/step - loss: 0.5343 - tp: 1.0000 - fp: 1.4912 - tn: 2326.5789 - fn: 569.1754 - accuracy: 0.8035 - precision: 0.4649 - recall: 0.0043 - auc: 0.4599 - prc: 0.1971 - val_loss: 0.5382 - val_tp: 0.0000e+00 - val_fp: 0.0000e+00 - val_tn: 1083.0000 - val_fn: 317.0000 - val_accuracy: 0.7736 - val_precision: 0.0000e+00 - val_recall: 0.0000e+00 - val_auc: 0.5530 - val_prc: 0.3012
Epoch 2/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4975 - tp: 0.0000e+00 - fp: 0.5965 - tn: 2333.8246 - fn: 563.8246 - accuracy: 0.8092 - precision: 0.0000e+00 - recall: 0.0000e+00 - auc: 0.5487 - prc: 0.2361 - val_loss: 0.5152 - val_tp: 1.0000 - val_fp: 1.0000 - val_tn: 1082.0000 - val_fn: 316.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.0032 - val_auc: 0.6409 - val_prc: 0.3459
Epoch 3/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4740 - tp: 2.2807 - fp: 2.5965 - tn: 2329.4035 - fn: 563.9649 - accuracy: 0.8072 - precision: 0.3079 - recall: 0.0027 - auc: 0.6514 - prc: 0.3132 - val_loss: 0.4976 - val_tp: 6.0000 - val_fp: 9.0000 - val_tn: 1074.0000 - val_fn: 311.0000 - val_accuracy: 0.7714 - val_precision: 0.4000 - val_recall: 0.0189 - val_auc: 0.6906 - val_prc: 0.3874
Epoch 4/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4580 - tp: 14.4737 - fp: 10.0351 - tn: 2326.8772 - fn: 546.8596 - accuracy: 0.8072 - precision: 0.5191 - recall: 0.0209 - auc: 0.6976 - prc: 0.3668 - val_loss: 0.4843 - val_tp: 17.0000 - val_fp: 16.0000 - val_tn: 1067.0000 - val_fn: 300.0000 - val_accuracy: 0.7743 - val_precision: 0.5152 - val_recall: 0.0536 - val_auc: 0.7169 - val_prc: 0.4193
Epoch 5/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4504 - tp: 41.3860 - fp: 26.7895 - tn: 2298.4561 - fn: 531.6140 - accuracy: 0.8062 - precision: 0.5750 - recall: 0.0656 - auc: 0.7205 - prc: 0.4110 - val_loss: 0.4743 - val_tp: 32.0000 - val_fp: 21.0000 - val_tn: 1062.0000 - val_fn: 285.0000 - val_accuracy: 0.7814 - val_precision: 0.6038 - val_recall: 0.1009 - val_auc: 0.7332 - val_prc: 0.4506
Epoch 6/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4378 - tp: 65.1404 - fp: 32.8070 - tn: 2287.2456 - fn: 513.0526 - accuracy: 0.8091 - precision: 0.6988 - recall: 0.1097 - auc: 0.7549 - prc: 0.4855 - val_loss: 0.4665 - val_tp: 46.0000 - val_fp: 19.0000 - val_tn: 1064.0000 - val_fn: 271.0000 - val_accuracy: 0.7929 - val_precision: 0.7077 - val_recall: 0.1451 - val_auc: 0.7446 - val_prc: 0.4818
Epoch 7/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4308 - tp: 97.1930 - fp: 35.6667 - tn: 2284.0000 - fn: 481.3860 - accuracy: 0.8201 - precision: 0.7388 - recall: 0.1639 - auc: 0.7576 - prc: 0.5049 - val_loss: 0.4591 - val_tp: 59.0000 - val_fp: 26.0000 - val_tn: 1057.0000 - val_fn: 258.0000 - val_accuracy: 0.7971 - val_precision: 0.6941 - val_recall: 0.1861 - val_auc: 0.7550 - val_prc: 0.5049
Epoch 8/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4197 - tp: 114.6667 - fp: 41.0351 - tn: 2289.2105 - fn: 453.3333 - accuracy: 0.8317 - precision: 0.7422 - recall: 0.2050 - auc: 0.7574 - prc: 0.5070 - val_loss: 0.4536 - val_tp: 67.0000 - val_fp: 28.0000 - val_tn: 1055.0000 - val_fn: 250.0000 - val_accuracy: 0.8014 - val_precision: 0.7053 - val_recall: 0.2114 - val_auc: 0.7625 - val_prc: 0.5208
Epoch 9/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4144 - tp: 133.0000 - fp: 46.8772 - tn: 2282.1930 - fn: 436.1754 - accuracy: 0.8353 - precision: 0.7506 - recall: 0.2365 - auc: 0.7699 - prc: 0.5190 - val_loss: 0.4492 - val_tp: 72.0000 - val_fp: 30.0000 - val_tn: 1053.0000 - val_fn: 245.0000 - val_accuracy: 0.8036 - val_precision: 0.7059 - val_recall: 0.2271 - val_auc: 0.7689 - val_prc: 0.5329
Epoch 10/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4143 - tp: 146.8772 - fp: 55.1228 - tn: 2271.4211 - fn: 424.8246 - accuracy: 0.8316 - precision: 0.7104 - recall: 0.2549 - auc: 0.7740 - prc: 0.5275 - val_loss: 0.4447 - val_tp: 78.0000 - val_fp: 32.0000 - val_tn: 1051.0000 - val_fn: 239.0000 - val_accuracy: 0.8064 - val_precision: 0.7091 - val_recall: 0.2461 - val_auc: 0.7748 - val_prc: 0.5471
Epoch 11/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4031 - tp: 172.5965 - fp: 52.7544 - tn: 2257.3860 - fn: 415.5088 - accuracy: 0.8416 - precision: 0.7959 - recall: 0.3074 - auc: 0.7994 - prc: 0.5933 - val_loss: 0.4431 - val_tp: 77.0000 - val_fp: 30.0000 - val_tn: 1053.0000 - val_fn: 240.0000 - val_accuracy: 0.8071 - val_precision: 0.7196 - val_recall: 0.2429 - val_auc: 0.7782 - val_prc: 0.5551
Epoch 12/100
56/56 [==============================] - 0s 1ms/step - loss: 0.4010 - tp: 151.2982 - fp: 49.3158 - tn: 2278.1228 - fn: 419.5088 - accuracy: 0.8378 - precision: 0.7686 - recall: 0.2686 - auc: 0.7943 - prc: 0.5627 - val_loss: 0.4387 - val_tp: 86.0000 - val_fp: 33.0000 - val_tn: 1050.0000 - val_fn: 231.0000 - val_accuracy: 0.8114 - val_precision: 0.7227 - val_recall: 0.2713 - val_auc: 0.7830 - val_prc: 0.5649
Epoch 13/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3929 - tp: 162.7193 - fp: 58.7368 - tn: 2269.2281 - fn: 407.5614 - accuracy: 0.8384 - precision: 0.7228 - recall: 0.2780 - auc: 0.8000 - prc: 0.5550 - val_loss: 0.4355 - val_tp: 90.0000 - val_fp: 34.0000 - val_tn: 1049.0000 - val_fn: 227.0000 - val_accuracy: 0.8136 - val_precision: 0.7258 - val_recall: 0.2839 - val_auc: 0.7872 - val_prc: 0.5713
Epoch 14/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3919 - tp: 186.1053 - fp: 66.2105 - tn: 2249.0526 - fn: 396.8772 - accuracy: 0.8383 - precision: 0.7312 - recall: 0.3236 - auc: 0.8098 - prc: 0.5980 - val_loss: 0.4335 - val_tp: 90.0000 - val_fp: 33.0000 - val_tn: 1050.0000 - val_fn: 227.0000 - val_accuracy: 0.8143 - val_precision: 0.7317 - val_recall: 0.2839 - val_auc: 0.7911 - val_prc: 0.5786
Epoch 15/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3836 - tp: 180.6491 - fp: 58.0000 - tn: 2270.4912 - fn: 389.1053 - accuracy: 0.8492 - precision: 0.7747 - recall: 0.3354 - auc: 0.8130 - prc: 0.6031 - val_loss: 0.4307 - val_tp: 92.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 225.0000 - val_accuracy: 0.8136 - val_precision: 0.7188 - val_recall: 0.2902 - val_auc: 0.7940 - val_prc: 0.5837
Epoch 16/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3897 - tp: 187.8772 - fp: 71.4737 - tn: 2244.3333 - fn: 394.5614 - accuracy: 0.8404 - precision: 0.7433 - recall: 0.3245 - auc: 0.8104 - prc: 0.6009 - val_loss: 0.4286 - val_tp: 94.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 223.0000 - val_accuracy: 0.8150 - val_precision: 0.7231 - val_recall: 0.2965 - val_auc: 0.7973 - val_prc: 0.5892
Epoch 17/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3812 - tp: 187.6140 - fp: 59.9123 - tn: 2260.5614 - fn: 390.1579 - accuracy: 0.8448 - precision: 0.7509 - recall: 0.3284 - auc: 0.8186 - prc: 0.5929 - val_loss: 0.4255 - val_tp: 98.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 219.0000 - val_accuracy: 0.8143 - val_precision: 0.7050 - val_recall: 0.3091 - val_auc: 0.7996 - val_prc: 0.5936
Epoch 18/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3834 - tp: 189.4561 - fp: 64.4211 - tn: 2256.6316 - fn: 387.7368 - accuracy: 0.8423 - precision: 0.7441 - recall: 0.3240 - auc: 0.8146 - prc: 0.6102 - val_loss: 0.4231 - val_tp: 100.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 217.0000 - val_accuracy: 0.8150 - val_precision: 0.7042 - val_recall: 0.3155 - val_auc: 0.8031 - val_prc: 0.5984
Epoch 19/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3877 - tp: 193.2281 - fp: 65.8596 - tn: 2258.6842 - fn: 380.4737 - accuracy: 0.8420 - precision: 0.7321 - recall: 0.3377 - auc: 0.8092 - prc: 0.5893 - val_loss: 0.4209 - val_tp: 100.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 217.0000 - val_accuracy: 0.8179 - val_precision: 0.7246 - val_recall: 0.3155 - val_auc: 0.8059 - val_prc: 0.6051
Epoch 20/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3797 - tp: 205.6842 - fp: 64.7018 - tn: 2251.3684 - fn: 376.4912 - accuracy: 0.8463 - precision: 0.7677 - recall: 0.3504 - auc: 0.8223 - prc: 0.6320 - val_loss: 0.4193 - val_tp: 99.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 218.0000 - val_accuracy: 0.8186 - val_precision: 0.7333 - val_recall: 0.3123 - val_auc: 0.8080 - val_prc: 0.6085
Epoch 21/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3742 - tp: 215.5965 - fp: 64.6667 - tn: 2243.2105 - fn: 374.7719 - accuracy: 0.8462 - precision: 0.7712 - recall: 0.3589 - auc: 0.8351 - prc: 0.6387 - val_loss: 0.4171 - val_tp: 102.0000 - val_fp: 34.0000 - val_tn: 1049.0000 - val_fn: 215.0000 - val_accuracy: 0.8221 - val_precision: 0.7500 - val_recall: 0.3218 - val_auc: 0.8108 - val_prc: 0.6150
Epoch 22/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3758 - tp: 194.8070 - fp: 63.2632 - tn: 2263.1053 - fn: 377.0702 - accuracy: 0.8461 - precision: 0.7431 - recall: 0.3273 - auc: 0.8211 - prc: 0.5945 - val_loss: 0.4146 - val_tp: 105.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 212.0000 - val_accuracy: 0.8221 - val_precision: 0.7394 - val_recall: 0.3312 - val_auc: 0.8127 - val_prc: 0.6180
Epoch 23/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3583 - tp: 217.3158 - fp: 66.0877 - tn: 2265.7719 - fn: 349.0702 - accuracy: 0.8597 - precision: 0.7677 - recall: 0.3912 - auc: 0.8345 - prc: 0.6406 - val_loss: 0.4120 - val_tp: 108.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 209.0000 - val_accuracy: 0.8229 - val_precision: 0.7347 - val_recall: 0.3407 - val_auc: 0.8150 - val_prc: 0.6213
Epoch 24/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3756 - tp: 221.4035 - fp: 77.6667 - tn: 2239.0877 - fn: 360.0877 - accuracy: 0.8469 - precision: 0.7400 - recall: 0.3800 - auc: 0.8273 - prc: 0.6237 - val_loss: 0.4105 - val_tp: 106.0000 - val_fp: 35.0000 - val_tn: 1048.0000 - val_fn: 211.0000 - val_accuracy: 0.8243 - val_precision: 0.7518 - val_recall: 0.3344 - val_auc: 0.8179 - val_prc: 0.6263
Epoch 25/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3630 - tp: 206.4211 - fp: 68.9123 - tn: 2267.9123 - fn: 355.0000 - accuracy: 0.8532 - precision: 0.7296 - recall: 0.3611 - auc: 0.8288 - prc: 0.5937 - val_loss: 0.4077 - val_tp: 115.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 202.0000 - val_accuracy: 0.8286 - val_precision: 0.7516 - val_recall: 0.3628 - val_auc: 0.8195 - val_prc: 0.6283
Epoch 26/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3764 - tp: 229.4211 - fp: 80.0000 - tn: 2230.5789 - fn: 358.2456 - accuracy: 0.8419 - precision: 0.7306 - recall: 0.3790 - auc: 0.8324 - prc: 0.6363 - val_loss: 0.4071 - val_tp: 111.0000 - val_fp: 34.0000 - val_tn: 1049.0000 - val_fn: 206.0000 - val_accuracy: 0.8286 - val_precision: 0.7655 - val_recall: 0.3502 - val_auc: 0.8221 - val_prc: 0.6331
Epoch 27/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3602 - tp: 215.3509 - fp: 68.2982 - tn: 2261.8421 - fn: 352.7544 - accuracy: 0.8561 - precision: 0.7647 - recall: 0.3920 - auc: 0.8382 - prc: 0.6403 - val_loss: 0.4038 - val_tp: 116.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 201.0000 - val_accuracy: 0.8300 - val_precision: 0.7582 - val_recall: 0.3659 - val_auc: 0.8236 - val_prc: 0.6351
Epoch 28/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3603 - tp: 233.7193 - fp: 73.7719 - tn: 2238.9825 - fn: 351.7719 - accuracy: 0.8514 - precision: 0.7728 - recall: 0.3984 - auc: 0.8492 - prc: 0.6577 - val_loss: 0.4031 - val_tp: 114.0000 - val_fp: 35.0000 - val_tn: 1048.0000 - val_fn: 203.0000 - val_accuracy: 0.8300 - val_precision: 0.7651 - val_recall: 0.3596 - val_auc: 0.8246 - val_prc: 0.6382
Epoch 29/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3693 - tp: 215.5965 - fp: 71.4211 - tn: 2250.1228 - fn: 361.1053 - accuracy: 0.8479 - precision: 0.7587 - recall: 0.3664 - auc: 0.8333 - prc: 0.6354 - val_loss: 0.4013 - val_tp: 116.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 201.0000 - val_accuracy: 0.8307 - val_precision: 0.7632 - val_recall: 0.3659 - val_auc: 0.8268 - val_prc: 0.6419
Epoch 30/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3720 - tp: 231.5263 - fp: 77.8947 - tn: 2234.7018 - fn: 354.1228 - accuracy: 0.8479 - precision: 0.7611 - recall: 0.4003 - auc: 0.8376 - prc: 0.6463 - val_loss: 0.3995 - val_tp: 118.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 199.0000 - val_accuracy: 0.8307 - val_precision: 0.7564 - val_recall: 0.3722 - val_auc: 0.8280 - val_prc: 0.6428
Epoch 31/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3514 - tp: 234.5439 - fp: 71.7018 - tn: 2255.8070 - fn: 336.1930 - accuracy: 0.8612 - precision: 0.7534 - recall: 0.4042 - auc: 0.8385 - prc: 0.6419 - val_loss: 0.3976 - val_tp: 121.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 196.0000 - val_accuracy: 0.8314 - val_precision: 0.7516 - val_recall: 0.3817 - val_auc: 0.8291 - val_prc: 0.6448
Epoch 32/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3567 - tp: 238.5439 - fp: 81.7544 - tn: 2239.6316 - fn: 338.3158 - accuracy: 0.8534 - precision: 0.7437 - recall: 0.4131 - auc: 0.8439 - prc: 0.6558 - val_loss: 0.3963 - val_tp: 121.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 196.0000 - val_accuracy: 0.8321 - val_precision: 0.7563 - val_recall: 0.3817 - val_auc: 0.8304 - val_prc: 0.6487
Epoch 33/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3375 - tp: 235.6842 - fp: 71.7193 - tn: 2265.6140 - fn: 325.2281 - accuracy: 0.8664 - precision: 0.7816 - recall: 0.4234 - auc: 0.8585 - prc: 0.6661 - val_loss: 0.3958 - val_tp: 120.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 197.0000 - val_accuracy: 0.8336 - val_precision: 0.7692 - val_recall: 0.3785 - val_auc: 0.8320 - val_prc: 0.6522
Epoch 34/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3495 - tp: 234.1228 - fp: 70.8596 - tn: 2260.5614 - fn: 332.7018 - accuracy: 0.8614 - precision: 0.7599 - recall: 0.4124 - auc: 0.8420 - prc: 0.6486 - val_loss: 0.3932 - val_tp: 128.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 189.0000 - val_accuracy: 0.8364 - val_precision: 0.7619 - val_recall: 0.4038 - val_auc: 0.8331 - val_prc: 0.6539
Epoch 35/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3471 - tp: 252.1404 - fp: 79.5965 - tn: 2240.7719 - fn: 325.7368 - accuracy: 0.8622 - precision: 0.7745 - recall: 0.4382 - auc: 0.8524 - prc: 0.6704 - val_loss: 0.3941 - val_tp: 121.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 196.0000 - val_accuracy: 0.8336 - val_precision: 0.7658 - val_recall: 0.3817 - val_auc: 0.8343 - val_prc: 0.6552
Epoch 36/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3611 - tp: 248.1754 - fp: 84.1053 - tn: 2227.9123 - fn: 338.0526 - accuracy: 0.8510 - precision: 0.7634 - recall: 0.4215 - auc: 0.8485 - prc: 0.6735 - val_loss: 0.3936 - val_tp: 120.0000 - val_fp: 35.0000 - val_tn: 1048.0000 - val_fn: 197.0000 - val_accuracy: 0.8343 - val_precision: 0.7742 - val_recall: 0.3785 - val_auc: 0.8355 - val_prc: 0.6571
Epoch 37/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3419 - tp: 244.0526 - fp: 71.2632 - tn: 2244.3860 - fn: 338.5439 - accuracy: 0.8591 - precision: 0.7884 - recall: 0.4089 - auc: 0.8594 - prc: 0.6878 - val_loss: 0.3914 - val_tp: 132.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 185.0000 - val_accuracy: 0.8400 - val_precision: 0.7719 - val_recall: 0.4164 - val_auc: 0.8355 - val_prc: 0.6577
Epoch 38/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3367 - tp: 240.1930 - fp: 67.0526 - tn: 2258.2807 - fn: 332.7193 - accuracy: 0.8642 - precision: 0.7965 - recall: 0.4160 - auc: 0.8605 - prc: 0.6873 - val_loss: 0.3899 - val_tp: 133.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 184.0000 - val_accuracy: 0.8407 - val_precision: 0.7733 - val_recall: 0.4196 - val_auc: 0.8368 - val_prc: 0.6620
Epoch 39/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3438 - tp: 245.5439 - fp: 72.5789 - tn: 2254.0351 - fn: 326.0877 - accuracy: 0.8646 - precision: 0.7712 - recall: 0.4396 - auc: 0.8519 - prc: 0.6684 - val_loss: 0.3885 - val_tp: 136.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 181.0000 - val_accuracy: 0.8407 - val_precision: 0.7640 - val_recall: 0.4290 - val_auc: 0.8374 - val_prc: 0.6642
Epoch 40/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3394 - tp: 243.6316 - fp: 72.7193 - tn: 2258.5614 - fn: 323.3333 - accuracy: 0.8671 - precision: 0.7806 - recall: 0.4252 - auc: 0.8468 - prc: 0.6720 - val_loss: 0.3889 - val_tp: 133.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 184.0000 - val_accuracy: 0.8421 - val_precision: 0.7824 - val_recall: 0.4196 - val_auc: 0.8383 - val_prc: 0.6657
Epoch 41/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3395 - tp: 246.0351 - fp: 76.2456 - tn: 2249.0877 - fn: 326.8772 - accuracy: 0.8626 - precision: 0.7721 - recall: 0.4254 - auc: 0.8552 - prc: 0.6779 - val_loss: 0.3867 - val_tp: 136.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 181.0000 - val_accuracy: 0.8414 - val_precision: 0.7684 - val_recall: 0.4290 - val_auc: 0.8390 - val_prc: 0.6668
Epoch 42/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3480 - tp: 250.0000 - fp: 80.5439 - tn: 2242.8772 - fn: 324.8246 - accuracy: 0.8581 - precision: 0.7562 - recall: 0.4378 - auc: 0.8508 - prc: 0.6786 - val_loss: 0.3880 - val_tp: 136.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 181.0000 - val_accuracy: 0.8414 - val_precision: 0.7684 - val_recall: 0.4290 - val_auc: 0.8384 - val_prc: 0.6679
Epoch 43/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3462 - tp: 259.9298 - fp: 90.4035 - tn: 2219.8421 - fn: 328.0702 - accuracy: 0.8553 - precision: 0.7445 - recall: 0.4460 - auc: 0.8589 - prc: 0.6844 - val_loss: 0.3875 - val_tp: 135.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 182.0000 - val_accuracy: 0.8414 - val_precision: 0.7714 - val_recall: 0.4259 - val_auc: 0.8389 - val_prc: 0.6696
Epoch 44/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3363 - tp: 235.8772 - fp: 82.0175 - tn: 2255.2982 - fn: 325.0526 - accuracy: 0.8587 - precision: 0.7204 - recall: 0.4286 - auc: 0.8575 - prc: 0.6538 - val_loss: 0.3853 - val_tp: 139.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 178.0000 - val_accuracy: 0.8393 - val_precision: 0.7473 - val_recall: 0.4385 - val_auc: 0.8393 - val_prc: 0.6696
Epoch 45/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3516 - tp: 252.4386 - fp: 87.6667 - tn: 2231.1930 - fn: 326.9474 - accuracy: 0.8535 - precision: 0.7441 - recall: 0.4206 - auc: 0.8501 - prc: 0.6720 - val_loss: 0.3885 - val_tp: 133.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 184.0000 - val_accuracy: 0.8421 - val_precision: 0.7824 - val_recall: 0.4196 - val_auc: 0.8397 - val_prc: 0.6716
Epoch 46/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3331 - tp: 248.1930 - fp: 75.0351 - tn: 2252.3509 - fn: 322.6667 - accuracy: 0.8634 - precision: 0.7688 - recall: 0.4312 - auc: 0.8640 - prc: 0.6816 - val_loss: 0.3851 - val_tp: 139.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 178.0000 - val_accuracy: 0.8400 - val_precision: 0.7514 - val_recall: 0.4385 - val_auc: 0.8408 - val_prc: 0.6734
Epoch 47/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3504 - tp: 246.3860 - fp: 87.8596 - tn: 2233.6842 - fn: 330.3158 - accuracy: 0.8513 - precision: 0.7192 - recall: 0.4130 - auc: 0.8474 - prc: 0.6590 - val_loss: 0.3853 - val_tp: 138.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 179.0000 - val_accuracy: 0.8393 - val_precision: 0.7500 - val_recall: 0.4353 - val_auc: 0.8408 - val_prc: 0.6740
Epoch 48/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3328 - tp: 243.8070 - fp: 75.2456 - tn: 2260.3333 - fn: 318.8596 - accuracy: 0.8672 - precision: 0.7748 - recall: 0.4397 - auc: 0.8565 - prc: 0.6923 - val_loss: 0.3833 - val_tp: 142.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 175.0000 - val_accuracy: 0.8400 - val_precision: 0.7435 - val_recall: 0.4479 - val_auc: 0.8406 - val_prc: 0.6746
Epoch 49/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3505 - tp: 266.7719 - fp: 90.5965 - tn: 2215.4737 - fn: 325.4035 - accuracy: 0.8568 - precision: 0.7552 - recall: 0.4523 - auc: 0.8536 - prc: 0.6787 - val_loss: 0.3846 - val_tp: 138.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 179.0000 - val_accuracy: 0.8400 - val_precision: 0.7541 - val_recall: 0.4353 - val_auc: 0.8414 - val_prc: 0.6756
Epoch 50/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3306 - tp: 245.9649 - fp: 75.7544 - tn: 2253.0000 - fn: 323.5263 - accuracy: 0.8620 - precision: 0.7585 - recall: 0.4231 - auc: 0.8635 - prc: 0.6841 - val_loss: 0.3824 - val_tp: 143.0000 - val_fp: 48.0000 - val_tn: 1035.0000 - val_fn: 174.0000 - val_accuracy: 0.8414 - val_precision: 0.7487 - val_recall: 0.4511 - val_auc: 0.8423 - val_prc: 0.6771
Epoch 51/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3320 - tp: 262.3509 - fp: 88.5088 - tn: 2236.0702 - fn: 311.3158 - accuracy: 0.8607 - precision: 0.7291 - recall: 0.4515 - auc: 0.8645 - prc: 0.6820 - val_loss: 0.3822 - val_tp: 143.0000 - val_fp: 48.0000 - val_tn: 1035.0000 - val_fn: 174.0000 - val_accuracy: 0.8414 - val_precision: 0.7487 - val_recall: 0.4511 - val_auc: 0.8419 - val_prc: 0.6779
Epoch 52/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3361 - tp: 254.4035 - fp: 84.6316 - tn: 2247.6491 - fn: 311.5614 - accuracy: 0.8629 - precision: 0.7484 - recall: 0.4557 - auc: 0.8606 - prc: 0.6783 - val_loss: 0.3816 - val_tp: 143.0000 - val_fp: 48.0000 - val_tn: 1035.0000 - val_fn: 174.0000 - val_accuracy: 0.8414 - val_precision: 0.7487 - val_recall: 0.4511 - val_auc: 0.8425 - val_prc: 0.6784
Epoch 53/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3353 - tp: 254.5614 - fp: 84.5965 - tn: 2245.5614 - fn: 313.5263 - accuracy: 0.8624 - precision: 0.7453 - recall: 0.4540 - auc: 0.8582 - prc: 0.6856 - val_loss: 0.3808 - val_tp: 144.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 173.0000 - val_accuracy: 0.8414 - val_precision: 0.7461 - val_recall: 0.4543 - val_auc: 0.8427 - val_prc: 0.6796
Epoch 54/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3285 - tp: 275.7895 - fp: 84.6842 - tn: 2226.5088 - fn: 311.2632 - accuracy: 0.8660 - precision: 0.7709 - recall: 0.4817 - auc: 0.8706 - prc: 0.7144 - val_loss: 0.3816 - val_tp: 140.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 177.0000 - val_accuracy: 0.8436 - val_precision: 0.7692 - val_recall: 0.4416 - val_auc: 0.8440 - val_prc: 0.6819
Epoch 55/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3319 - tp: 267.8070 - fp: 75.1754 - tn: 2241.4386 - fn: 313.8246 - accuracy: 0.8685 - precision: 0.8034 - recall: 0.4690 - auc: 0.8694 - prc: 0.7136 - val_loss: 0.3820 - val_tp: 140.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 177.0000 - val_accuracy: 0.8443 - val_precision: 0.7735 - val_recall: 0.4416 - val_auc: 0.8444 - val_prc: 0.6823
Epoch 56/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3431 - tp: 267.4035 - fp: 85.2281 - tn: 2226.0526 - fn: 319.5614 - accuracy: 0.8562 - precision: 0.7535 - recall: 0.4533 - auc: 0.8625 - prc: 0.6934 - val_loss: 0.3825 - val_tp: 140.0000 - val_fp: 35.0000 - val_tn: 1048.0000 - val_fn: 177.0000 - val_accuracy: 0.8486 - val_precision: 0.8000 - val_recall: 0.4416 - val_auc: 0.8453 - val_prc: 0.6830
Epoch 57/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3388 - tp: 254.3509 - fp: 83.2807 - tn: 2233.4561 - fn: 327.1579 - accuracy: 0.8591 - precision: 0.7507 - recall: 0.4405 - auc: 0.8598 - prc: 0.6859 - val_loss: 0.3792 - val_tp: 143.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 174.0000 - val_accuracy: 0.8429 - val_precision: 0.7566 - val_recall: 0.4511 - val_auc: 0.8452 - val_prc: 0.6840
Epoch 58/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3273 - tp: 242.8070 - fp: 72.9123 - tn: 2272.2456 - fn: 310.2807 - accuracy: 0.8679 - precision: 0.7550 - recall: 0.4367 - auc: 0.8610 - prc: 0.6700 - val_loss: 0.3786 - val_tp: 146.0000 - val_fp: 48.0000 - val_tn: 1035.0000 - val_fn: 171.0000 - val_accuracy: 0.8436 - val_precision: 0.7526 - val_recall: 0.4606 - val_auc: 0.8453 - val_prc: 0.6849
Epoch 59/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3277 - tp: 252.1754 - fp: 87.3684 - tn: 2250.0351 - fn: 308.6667 - accuracy: 0.8651 - precision: 0.7438 - recall: 0.4554 - auc: 0.8652 - prc: 0.6844 - val_loss: 0.3778 - val_tp: 144.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 173.0000 - val_accuracy: 0.8436 - val_precision: 0.7579 - val_recall: 0.4543 - val_auc: 0.8458 - val_prc: 0.6845
Epoch 60/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3466 - tp: 272.4561 - fp: 93.2456 - tn: 2213.1228 - fn: 319.4211 - accuracy: 0.8533 - precision: 0.7451 - recall: 0.4558 - auc: 0.8624 - prc: 0.6931 - val_loss: 0.3794 - val_tp: 141.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 176.0000 - val_accuracy: 0.8443 - val_precision: 0.7705 - val_recall: 0.4448 - val_auc: 0.8465 - val_prc: 0.6861
Epoch 61/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3320 - tp: 252.6842 - fp: 79.7368 - tn: 2247.3158 - fn: 318.5088 - accuracy: 0.8660 - precision: 0.7712 - recall: 0.4498 - auc: 0.8624 - prc: 0.6895 - val_loss: 0.3802 - val_tp: 143.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 174.0000 - val_accuracy: 0.8457 - val_precision: 0.7730 - val_recall: 0.4511 - val_auc: 0.8462 - val_prc: 0.6862
Epoch 62/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3319 - tp: 264.5263 - fp: 78.9298 - tn: 2242.0000 - fn: 312.7895 - accuracy: 0.8675 - precision: 0.7706 - recall: 0.4620 - auc: 0.8606 - prc: 0.6948 - val_loss: 0.3792 - val_tp: 143.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 174.0000 - val_accuracy: 0.8457 - val_precision: 0.7730 - val_recall: 0.4511 - val_auc: 0.8468 - val_prc: 0.6875
Epoch 63/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3341 - tp: 263.1579 - fp: 84.0526 - tn: 2238.7895 - fn: 312.2456 - accuracy: 0.8627 - precision: 0.7490 - recall: 0.4592 - auc: 0.8615 - prc: 0.6957 - val_loss: 0.3777 - val_tp: 143.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 174.0000 - val_accuracy: 0.8457 - val_precision: 0.7730 - val_recall: 0.4511 - val_auc: 0.8472 - val_prc: 0.6877
Epoch 64/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3274 - tp: 254.9649 - fp: 82.1053 - tn: 2249.5439 - fn: 311.6316 - accuracy: 0.8649 - precision: 0.7516 - recall: 0.4518 - auc: 0.8662 - prc: 0.6920 - val_loss: 0.3794 - val_tp: 140.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 177.0000 - val_accuracy: 0.8443 - val_precision: 0.7735 - val_recall: 0.4416 - val_auc: 0.8468 - val_prc: 0.6874
Epoch 65/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3211 - tp: 267.8772 - fp: 80.3684 - tn: 2247.6667 - fn: 302.3333 - accuracy: 0.8702 - precision: 0.7801 - recall: 0.4730 - auc: 0.8737 - prc: 0.7107 - val_loss: 0.3767 - val_tp: 146.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 171.0000 - val_accuracy: 0.8443 - val_precision: 0.7565 - val_recall: 0.4606 - val_auc: 0.8469 - val_prc: 0.6878
Epoch 66/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3364 - tp: 270.1930 - fp: 85.8772 - tn: 2231.2982 - fn: 310.8772 - accuracy: 0.8657 - precision: 0.7727 - recall: 0.4647 - auc: 0.8596 - prc: 0.6934 - val_loss: 0.3796 - val_tp: 137.0000 - val_fp: 34.0000 - val_tn: 1049.0000 - val_fn: 180.0000 - val_accuracy: 0.8471 - val_precision: 0.8012 - val_recall: 0.4322 - val_auc: 0.8473 - val_prc: 0.6887
Epoch 67/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3367 - tp: 245.0000 - fp: 69.1228 - tn: 2265.8772 - fn: 318.2456 - accuracy: 0.8649 - precision: 0.7693 - recall: 0.4271 - auc: 0.8554 - prc: 0.6702 - val_loss: 0.3768 - val_tp: 145.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 172.0000 - val_accuracy: 0.8457 - val_precision: 0.7672 - val_recall: 0.4574 - val_auc: 0.8477 - val_prc: 0.6879
Epoch 68/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3273 - tp: 276.0526 - fp: 76.9123 - tn: 2240.1228 - fn: 305.1579 - accuracy: 0.8686 - precision: 0.7995 - recall: 0.4710 - auc: 0.8698 - prc: 0.7191 - val_loss: 0.3773 - val_tp: 144.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 173.0000 - val_accuracy: 0.8457 - val_precision: 0.7701 - val_recall: 0.4543 - val_auc: 0.8479 - val_prc: 0.6893
Epoch 69/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3314 - tp: 275.4386 - fp: 80.2982 - tn: 2230.3333 - fn: 312.1754 - accuracy: 0.8612 - precision: 0.7781 - recall: 0.4552 - auc: 0.8738 - prc: 0.7093 - val_loss: 0.3773 - val_tp: 144.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 173.0000 - val_accuracy: 0.8450 - val_precision: 0.7660 - val_recall: 0.4543 - val_auc: 0.8477 - val_prc: 0.6886
Epoch 70/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3295 - tp: 266.2982 - fp: 82.2807 - tn: 2234.3509 - fn: 315.3158 - accuracy: 0.8633 - precision: 0.7755 - recall: 0.4584 - auc: 0.8709 - prc: 0.7088 - val_loss: 0.3774 - val_tp: 141.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 176.0000 - val_accuracy: 0.8436 - val_precision: 0.7663 - val_recall: 0.4448 - val_auc: 0.8479 - val_prc: 0.6892
Epoch 71/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3286 - tp: 271.0877 - fp: 77.1404 - tn: 2242.5088 - fn: 307.5088 - accuracy: 0.8656 - precision: 0.7826 - recall: 0.4637 - auc: 0.8710 - prc: 0.7164 - val_loss: 0.3767 - val_tp: 144.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 173.0000 - val_accuracy: 0.8457 - val_precision: 0.7701 - val_recall: 0.4543 - val_auc: 0.8481 - val_prc: 0.6897
Epoch 72/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3286 - tp: 255.9123 - fp: 75.7544 - tn: 2255.1930 - fn: 311.3860 - accuracy: 0.8659 - precision: 0.7620 - recall: 0.4380 - auc: 0.8604 - prc: 0.6896 - val_loss: 0.3753 - val_tp: 146.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 171.0000 - val_accuracy: 0.8457 - val_precision: 0.7644 - val_recall: 0.4606 - val_auc: 0.8478 - val_prc: 0.6898
Epoch 73/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3276 - tp: 267.1754 - fp: 82.2456 - tn: 2246.1930 - fn: 302.6316 - accuracy: 0.8658 - precision: 0.7607 - recall: 0.4701 - auc: 0.8680 - prc: 0.7039 - val_loss: 0.3764 - val_tp: 141.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 176.0000 - val_accuracy: 0.8443 - val_precision: 0.7705 - val_recall: 0.4448 - val_auc: 0.8484 - val_prc: 0.6905
Epoch 74/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3260 - tp: 262.3860 - fp: 78.4737 - tn: 2247.5439 - fn: 309.8421 - accuracy: 0.8671 - precision: 0.7743 - recall: 0.4556 - auc: 0.8675 - prc: 0.6972 - val_loss: 0.3757 - val_tp: 145.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 172.0000 - val_accuracy: 0.8450 - val_precision: 0.7632 - val_recall: 0.4574 - val_auc: 0.8481 - val_prc: 0.6899
Epoch 75/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3346 - tp: 281.3509 - fp: 83.3333 - tn: 2227.1579 - fn: 306.4035 - accuracy: 0.8642 - precision: 0.7753 - recall: 0.4731 - auc: 0.8660 - prc: 0.7073 - val_loss: 0.3770 - val_tp: 138.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 179.0000 - val_accuracy: 0.8429 - val_precision: 0.7709 - val_recall: 0.4353 - val_auc: 0.8491 - val_prc: 0.6920
Epoch 76/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3266 - tp: 261.4912 - fp: 76.4737 - tn: 2251.1754 - fn: 309.1053 - accuracy: 0.8674 - precision: 0.7752 - recall: 0.4561 - auc: 0.8656 - prc: 0.7010 - val_loss: 0.3759 - val_tp: 142.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 175.0000 - val_accuracy: 0.8450 - val_precision: 0.7717 - val_recall: 0.4479 - val_auc: 0.8486 - val_prc: 0.6910
Epoch 77/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3214 - tp: 278.8596 - fp: 87.8596 - tn: 2230.4386 - fn: 301.0877 - accuracy: 0.8664 - precision: 0.7617 - recall: 0.4879 - auc: 0.8751 - prc: 0.7225 - val_loss: 0.3761 - val_tp: 140.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 177.0000 - val_accuracy: 0.8429 - val_precision: 0.7650 - val_recall: 0.4416 - val_auc: 0.8487 - val_prc: 0.6910
Epoch 78/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3234 - tp: 262.3684 - fp: 76.0702 - tn: 2260.6316 - fn: 299.1754 - accuracy: 0.8717 - precision: 0.7830 - recall: 0.4653 - auc: 0.8677 - prc: 0.6967 - val_loss: 0.3752 - val_tp: 144.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 173.0000 - val_accuracy: 0.8457 - val_precision: 0.7701 - val_recall: 0.4543 - val_auc: 0.8484 - val_prc: 0.6919
Epoch 79/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3230 - tp: 277.9123 - fp: 82.6316 - tn: 2241.0877 - fn: 296.6140 - accuracy: 0.8706 - precision: 0.7721 - recall: 0.4848 - auc: 0.8729 - prc: 0.7107 - val_loss: 0.3765 - val_tp: 140.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 177.0000 - val_accuracy: 0.8436 - val_precision: 0.7692 - val_recall: 0.4416 - val_auc: 0.8494 - val_prc: 0.6914
Epoch 80/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3232 - tp: 270.6316 - fp: 82.3333 - tn: 2240.8246 - fn: 304.4561 - accuracy: 0.8685 - precision: 0.7587 - recall: 0.4735 - auc: 0.8700 - prc: 0.6963 - val_loss: 0.3755 - val_tp: 141.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 176.0000 - val_accuracy: 0.8436 - val_precision: 0.7663 - val_recall: 0.4448 - val_auc: 0.8490 - val_prc: 0.6919
Epoch 81/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3367 - tp: 275.7018 - fp: 82.1754 - tn: 2229.5263 - fn: 310.8421 - accuracy: 0.8608 - precision: 0.7745 - recall: 0.4606 - auc: 0.8671 - prc: 0.7021 - val_loss: 0.3758 - val_tp: 140.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 177.0000 - val_accuracy: 0.8457 - val_precision: 0.7821 - val_recall: 0.4416 - val_auc: 0.8493 - val_prc: 0.6928
Epoch 82/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3412 - tp: 281.8772 - fp: 90.1579 - tn: 2212.5439 - fn: 313.6667 - accuracy: 0.8571 - precision: 0.7535 - recall: 0.4669 - auc: 0.8632 - prc: 0.7064 - val_loss: 0.3774 - val_tp: 138.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 179.0000 - val_accuracy: 0.8457 - val_precision: 0.7886 - val_recall: 0.4353 - val_auc: 0.8500 - val_prc: 0.6927
Epoch 83/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3226 - tp: 251.2456 - fp: 70.8772 - tn: 2264.7368 - fn: 311.3860 - accuracy: 0.8692 - precision: 0.7873 - recall: 0.4456 - auc: 0.8677 - prc: 0.7051 - val_loss: 0.3741 - val_tp: 145.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 172.0000 - val_accuracy: 0.8443 - val_precision: 0.7592 - val_recall: 0.4574 - val_auc: 0.8493 - val_prc: 0.6928
Epoch 84/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3243 - tp: 269.8246 - fp: 90.8246 - tn: 2229.5263 - fn: 308.0702 - accuracy: 0.8628 - precision: 0.7607 - recall: 0.4726 - auc: 0.8766 - prc: 0.7142 - val_loss: 0.3751 - val_tp: 141.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 176.0000 - val_accuracy: 0.8450 - val_precision: 0.7747 - val_recall: 0.4448 - val_auc: 0.8497 - val_prc: 0.6937
Epoch 85/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3220 - tp: 287.2982 - fp: 85.0702 - tn: 2226.1228 - fn: 299.7544 - accuracy: 0.8676 - precision: 0.7798 - recall: 0.4965 - auc: 0.8791 - prc: 0.7288 - val_loss: 0.3762 - val_tp: 139.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 178.0000 - val_accuracy: 0.8457 - val_precision: 0.7853 - val_recall: 0.4385 - val_auc: 0.8500 - val_prc: 0.6930
Epoch 86/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3356 - tp: 263.6491 - fp: 76.2982 - tn: 2247.9649 - fn: 310.3333 - accuracy: 0.8640 - precision: 0.7812 - recall: 0.4522 - auc: 0.8632 - prc: 0.6987 - val_loss: 0.3756 - val_tp: 141.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 176.0000 - val_accuracy: 0.8457 - val_precision: 0.7790 - val_recall: 0.4448 - val_auc: 0.8499 - val_prc: 0.6935
Epoch 87/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3190 - tp: 287.9825 - fp: 87.1053 - tn: 2231.2632 - fn: 291.8947 - accuracy: 0.8707 - precision: 0.7808 - recall: 0.5052 - auc: 0.8790 - prc: 0.7321 - val_loss: 0.3753 - val_tp: 141.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 176.0000 - val_accuracy: 0.8443 - val_precision: 0.7705 - val_recall: 0.4448 - val_auc: 0.8499 - val_prc: 0.6932
Epoch 88/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3206 - tp: 271.8246 - fp: 80.8070 - tn: 2253.8070 - fn: 291.8070 - accuracy: 0.8728 - precision: 0.7827 - recall: 0.4848 - auc: 0.8721 - prc: 0.7103 - val_loss: 0.3756 - val_tp: 140.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 177.0000 - val_accuracy: 0.8450 - val_precision: 0.7778 - val_recall: 0.4416 - val_auc: 0.8500 - val_prc: 0.6939
Epoch 89/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3277 - tp: 270.8596 - fp: 89.5789 - tn: 2238.1053 - fn: 299.7018 - accuracy: 0.8647 - precision: 0.7545 - recall: 0.4613 - auc: 0.8669 - prc: 0.6949 - val_loss: 0.3758 - val_tp: 139.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 178.0000 - val_accuracy: 0.8429 - val_precision: 0.7680 - val_recall: 0.4385 - val_auc: 0.8499 - val_prc: 0.6941
Epoch 90/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3396 - tp: 272.6667 - fp: 86.9474 - tn: 2228.8947 - fn: 309.7368 - accuracy: 0.8580 - precision: 0.7479 - recall: 0.4614 - auc: 0.8641 - prc: 0.6904 - val_loss: 0.3746 - val_tp: 142.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 175.0000 - val_accuracy: 0.8443 - val_precision: 0.7676 - val_recall: 0.4479 - val_auc: 0.8503 - val_prc: 0.6946
Epoch 91/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3250 - tp: 279.4737 - fp: 82.7193 - tn: 2243.4386 - fn: 292.6140 - accuracy: 0.8693 - precision: 0.7731 - recall: 0.4895 - auc: 0.8691 - prc: 0.7153 - val_loss: 0.3743 - val_tp: 145.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 172.0000 - val_accuracy: 0.8443 - val_precision: 0.7592 - val_recall: 0.4574 - val_auc: 0.8497 - val_prc: 0.6943
Epoch 92/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3279 - tp: 288.3158 - fp: 87.1579 - tn: 2223.8596 - fn: 298.9123 - accuracy: 0.8676 - precision: 0.7811 - recall: 0.5019 - auc: 0.8739 - prc: 0.7243 - val_loss: 0.3748 - val_tp: 141.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 176.0000 - val_accuracy: 0.8450 - val_precision: 0.7747 - val_recall: 0.4448 - val_auc: 0.8502 - val_prc: 0.6946
Epoch 93/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3169 - tp: 281.5965 - fp: 79.0877 - tn: 2240.5263 - fn: 297.0351 - accuracy: 0.8741 - precision: 0.7924 - recall: 0.4998 - auc: 0.8786 - prc: 0.7262 - val_loss: 0.3750 - val_tp: 142.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 175.0000 - val_accuracy: 0.8414 - val_precision: 0.7513 - val_recall: 0.4479 - val_auc: 0.8501 - val_prc: 0.6936
Epoch 94/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3097 - tp: 262.9123 - fp: 78.7368 - tn: 2260.7018 - fn: 295.8947 - accuracy: 0.8763 - precision: 0.7654 - recall: 0.4781 - auc: 0.8753 - prc: 0.6994 - val_loss: 0.3735 - val_tp: 145.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 172.0000 - val_accuracy: 0.8443 - val_precision: 0.7592 - val_recall: 0.4574 - val_auc: 0.8501 - val_prc: 0.6950
Epoch 95/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3258 - tp: 270.7193 - fp: 93.4386 - tn: 2228.9123 - fn: 305.1754 - accuracy: 0.8615 - precision: 0.7407 - recall: 0.4655 - auc: 0.8699 - prc: 0.7065 - val_loss: 0.3754 - val_tp: 139.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 178.0000 - val_accuracy: 0.8436 - val_precision: 0.7722 - val_recall: 0.4385 - val_auc: 0.8506 - val_prc: 0.6955
Epoch 96/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3194 - tp: 251.6491 - fp: 74.2807 - tn: 2261.7368 - fn: 310.5789 - accuracy: 0.8695 - precision: 0.7703 - recall: 0.4523 - auc: 0.8717 - prc: 0.6932 - val_loss: 0.3738 - val_tp: 145.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 172.0000 - val_accuracy: 0.8421 - val_precision: 0.7474 - val_recall: 0.4574 - val_auc: 0.8509 - val_prc: 0.6952
Epoch 97/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3212 - tp: 288.4035 - fp: 89.0526 - tn: 2223.5263 - fn: 297.2632 - accuracy: 0.8677 - precision: 0.7711 - recall: 0.4948 - auc: 0.8780 - prc: 0.7219 - val_loss: 0.3761 - val_tp: 139.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 178.0000 - val_accuracy: 0.8429 - val_precision: 0.7680 - val_recall: 0.4385 - val_auc: 0.8507 - val_prc: 0.6951
Epoch 98/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3322 - tp: 272.4561 - fp: 85.7895 - tn: 2238.4211 - fn: 301.5789 - accuracy: 0.8606 - precision: 0.7497 - recall: 0.4527 - auc: 0.8658 - prc: 0.6959 - val_loss: 0.3756 - val_tp: 141.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 176.0000 - val_accuracy: 0.8436 - val_precision: 0.7663 - val_recall: 0.4448 - val_auc: 0.8508 - val_prc: 0.6951
Epoch 99/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3247 - tp: 270.0000 - fp: 82.2982 - tn: 2249.9825 - fn: 295.9649 - accuracy: 0.8691 - precision: 0.7535 - recall: 0.4743 - auc: 0.8656 - prc: 0.6923 - val_loss: 0.3742 - val_tp: 143.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 174.0000 - val_accuracy: 0.8407 - val_precision: 0.7448 - val_recall: 0.4511 - val_auc: 0.8509 - val_prc: 0.6948
Epoch 100/100
56/56 [==============================] - 0s 1ms/step - loss: 0.3238 - tp: 275.5088 - fp: 83.4035 - tn: 2235.4035 - fn: 303.9298 - accuracy: 0.8674 - precision: 0.7569 - recall: 0.4786 - auc: 0.8707 - prc: 0.7036 - val_loss: 0.3744 - val_tp: 143.0000 - val_fp: 48.0000 - val_tn: 1035.0000 - val_fn: 174.0000 - val_accuracy: 0.8414 - val_precision: 0.7487 - val_recall: 0.4511 - val_auc: 0.8508 - val_prc: 0.6947
CPU times: user 14.3 s, sys: 1.88 s, total: 16.2 s
Wall time: 9.95 s


model1.summary()

Model: "sequential_14"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_37 (Dense)             (None, 16)                192       
_________________________________________________________________
dense_38 (Dense)             (None, 1)                 17        
=================================================================
Total params: 209
Trainable params: 209
Non-trainable params: 0
_________________________________________________________________


history_df = pd.DataFrame(history1.history)
history_df['epoch']=history1.epoch
display(history_df)
train_acc = history_df.loc[99,'accuracy']
train_recall = history_df.loc[99,'recall']
train_loss = history_df.loc[99,'loss']


results1=model1.evaluate(X_test, y_test.values)
#print(model1.metrics_names)
#print(results1)

results_df = pd.DataFrame(results1, index=model1.metrics_names, columns=['model1'])

results_df

94/94 [==============================] - 1s 1ms/step - loss: 0.3472 - tp: 295.0000 - fp: 108.0000 - tn: 2281.0000 - fn: 316.0000 - accuracy: 0.8587 - precision: 0.7320 - recall: 0.4828 - auc: 0.8511 - prc: 0.6863


plt.figure(figsize=(10,10))
plot_metrics(history1)


# ANN return continuous nos from 0 to 1 as output
# we use a threshold of 0.5 to classify the output as 0 or 1


y_predict = (model1.predict(X_test) > THRESHOLD).astype('int32')

make_confusion_matrix(model1,y_test,y_predict, cmap='magma_r')


print(f'Model test loss is: {results_df.loc["loss","model1"]:0.4f}, train loss is {train_loss:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model1"]:0.4f}, train accuracy is {train_acc:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model1"]:0.4f}, train recall is {train_recall:0.4f}')

Model test loss is: 0.3472, train loss is 0.3230
Model test accuracy is: 0.8587, train accuracy is 0.8679
Model test recall is: 0.4828, train recall is 0.4833


# Source: https://www.tensorflow.org/tutorials/structured_data/imbalanced_data


# Scaling by total/2 helps keep the loss to a similar magnitude.
# The sum of the weights of all examples stays the same.
weight_for_0 = (1 / neg)*(total)/2.0 
weight_for_1 = (1 / pos)*(total)/2.0

class_weight = {0: weight_for_0, 1: weight_for_1}

print('Weight for class 0: {:.2f}'.format(weight_for_0))
print('Weight for class 1: {:.2f}'.format(weight_for_1))

Weight for class 0: 0.63
Weight for class 1: 2.45


model2 = make_model(dropout=True, learning_rate=0.001)

history2 = model2.fit(X_train, y_train, epochs=EPOCHS+100, batch_size=BATCH_SIZE, use_multiprocessing=True, validation_split=0.2, class_weight=class_weight)

Epoch 1/200
56/56 [==============================] - 2s 13ms/step - loss: 0.8087 - tp: 494.7719 - fp: 977.1579 - tn: 3725.4386 - fn: 700.8772 - accuracy: 0.7291 - precision: 0.3765 - recall: 0.4166 - auc: 0.7063 - prc: 0.4514 - val_loss: 0.6632 - val_tp: 139.0000 - val_fp: 381.0000 - val_tn: 702.0000 - val_fn: 178.0000 - val_accuracy: 0.6007 - val_precision: 0.2673 - val_recall: 0.4385 - val_auc: 0.5427 - val_prc: 0.2606
Epoch 2/200
56/56 [==============================] - 0s 1ms/step - loss: 0.7161 - tp: 304.7719 - fp: 989.6667 - tn: 1324.6140 - fn: 279.1930 - accuracy: 0.5633 - precision: 0.2388 - recall: 0.5161 - auc: 0.5553 - prc: 0.2634 - val_loss: 0.6517 - val_tp: 182.0000 - val_fp: 386.0000 - val_tn: 697.0000 - val_fn: 135.0000 - val_accuracy: 0.6279 - val_precision: 0.3204 - val_recall: 0.5741 - val_auc: 0.6389 - val_prc: 0.3522
Epoch 3/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6720 - tp: 339.0000 - fp: 946.5088 - tn: 1370.8596 - fn: 241.8772 - accuracy: 0.5899 - precision: 0.2664 - recall: 0.5874 - auc: 0.6209 - prc: 0.3041 - val_loss: 0.6405 - val_tp: 202.0000 - val_fp: 378.0000 - val_tn: 705.0000 - val_fn: 115.0000 - val_accuracy: 0.6479 - val_precision: 0.3483 - val_recall: 0.6372 - val_auc: 0.6978 - val_prc: 0.4092
Epoch 4/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6418 - tp: 370.9298 - fp: 912.9474 - tn: 1411.7193 - fn: 202.6491 - accuracy: 0.6149 - precision: 0.2893 - recall: 0.6539 - auc: 0.6730 - prc: 0.3422 - val_loss: 0.6298 - val_tp: 215.0000 - val_fp: 358.0000 - val_tn: 725.0000 - val_fn: 102.0000 - val_accuracy: 0.6714 - val_precision: 0.3752 - val_recall: 0.6782 - val_auc: 0.7293 - val_prc: 0.4318
Epoch 5/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6428 - tp: 363.4737 - fp: 870.8947 - tn: 1457.3860 - fn: 206.4912 - accuracy: 0.6264 - precision: 0.2930 - recall: 0.6401 - auc: 0.6732 - prc: 0.3541 - val_loss: 0.6207 - val_tp: 218.0000 - val_fp: 345.0000 - val_tn: 738.0000 - val_fn: 99.0000 - val_accuracy: 0.6829 - val_precision: 0.3872 - val_recall: 0.6877 - val_auc: 0.7431 - val_prc: 0.4404
Epoch 6/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6183 - tp: 386.8596 - fp: 853.9474 - tn: 1469.9649 - fn: 187.4737 - accuracy: 0.6372 - precision: 0.3120 - recall: 0.6839 - auc: 0.7113 - prc: 0.4082 - val_loss: 0.6147 - val_tp: 219.0000 - val_fp: 342.0000 - val_tn: 741.0000 - val_fn: 98.0000 - val_accuracy: 0.6857 - val_precision: 0.3904 - val_recall: 0.6909 - val_auc: 0.7514 - val_prc: 0.4460
Epoch 7/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6135 - tp: 373.7719 - fp: 790.1754 - tn: 1538.0351 - fn: 196.2632 - accuracy: 0.6571 - precision: 0.3158 - recall: 0.6411 - auc: 0.7124 - prc: 0.4035 - val_loss: 0.6094 - val_tp: 220.0000 - val_fp: 335.0000 - val_tn: 748.0000 - val_fn: 97.0000 - val_accuracy: 0.6914 - val_precision: 0.3964 - val_recall: 0.6940 - val_auc: 0.7568 - val_prc: 0.4536
Epoch 8/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6081 - tp: 378.0877 - fp: 814.4561 - tn: 1514.8772 - fn: 190.8246 - accuracy: 0.6511 - precision: 0.3108 - recall: 0.6555 - auc: 0.7155 - prc: 0.4031 - val_loss: 0.6064 - val_tp: 224.0000 - val_fp: 333.0000 - val_tn: 750.0000 - val_fn: 93.0000 - val_accuracy: 0.6957 - val_precision: 0.4022 - val_recall: 0.7066 - val_auc: 0.7626 - val_prc: 0.4606
Epoch 9/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6139 - tp: 403.6667 - fp: 779.5614 - tn: 1531.1930 - fn: 183.8246 - accuracy: 0.6654 - precision: 0.3467 - recall: 0.6830 - auc: 0.7333 - prc: 0.4429 - val_loss: 0.6033 - val_tp: 224.0000 - val_fp: 331.0000 - val_tn: 752.0000 - val_fn: 93.0000 - val_accuracy: 0.6971 - val_precision: 0.4036 - val_recall: 0.7066 - val_auc: 0.7676 - val_prc: 0.4677
Epoch 10/200
56/56 [==============================] - 0s 1ms/step - loss: 0.6006 - tp: 374.2456 - fp: 765.9649 - tn: 1568.3860 - fn: 189.6491 - accuracy: 0.6621 - precision: 0.3162 - recall: 0.6509 - auc: 0.7245 - prc: 0.3965 - val_loss: 0.5999 - val_tp: 226.0000 - val_fp: 319.0000 - val_tn: 764.0000 - val_fn: 91.0000 - val_accuracy: 0.7071 - val_precision: 0.4147 - val_recall: 0.7129 - val_auc: 0.7715 - val_prc: 0.4730
Epoch 11/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5957 - tp: 398.2105 - fp: 743.9649 - tn: 1579.3509 - fn: 176.7193 - accuracy: 0.6844 - precision: 0.3518 - recall: 0.6852 - auc: 0.7454 - prc: 0.4407 - val_loss: 0.5877 - val_tp: 219.0000 - val_fp: 299.0000 - val_tn: 784.0000 - val_fn: 98.0000 - val_accuracy: 0.7164 - val_precision: 0.4228 - val_recall: 0.6909 - val_auc: 0.7737 - val_prc: 0.4763
Epoch 12/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5876 - tp: 388.0351 - fp: 683.2456 - tn: 1647.4211 - fn: 179.5439 - accuracy: 0.6983 - precision: 0.3554 - recall: 0.6635 - auc: 0.7473 - prc: 0.4407 - val_loss: 0.5834 - val_tp: 220.0000 - val_fp: 298.0000 - val_tn: 785.0000 - val_fn: 97.0000 - val_accuracy: 0.7179 - val_precision: 0.4247 - val_recall: 0.6940 - val_auc: 0.7768 - val_prc: 0.4811
Epoch 13/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5898 - tp: 390.1053 - fp: 704.8947 - tn: 1623.6140 - fn: 179.6316 - accuracy: 0.6925 - precision: 0.3506 - recall: 0.6801 - auc: 0.7465 - prc: 0.4142 - val_loss: 0.5801 - val_tp: 220.0000 - val_fp: 291.0000 - val_tn: 792.0000 - val_fn: 97.0000 - val_accuracy: 0.7229 - val_precision: 0.4305 - val_recall: 0.6940 - val_auc: 0.7799 - val_prc: 0.4864
Epoch 14/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5859 - tp: 402.8246 - fp: 713.5789 - tn: 1601.7193 - fn: 180.1228 - accuracy: 0.6883 - precision: 0.3592 - recall: 0.6950 - auc: 0.7580 - prc: 0.4465 - val_loss: 0.5752 - val_tp: 218.0000 - val_fp: 284.0000 - val_tn: 799.0000 - val_fn: 99.0000 - val_accuracy: 0.7264 - val_precision: 0.4343 - val_recall: 0.6877 - val_auc: 0.7829 - val_prc: 0.4932
Epoch 15/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5809 - tp: 388.5088 - fp: 696.9825 - tn: 1635.2456 - fn: 177.5088 - accuracy: 0.6933 - precision: 0.3501 - recall: 0.6865 - auc: 0.7569 - prc: 0.4551 - val_loss: 0.5715 - val_tp: 220.0000 - val_fp: 278.0000 - val_tn: 805.0000 - val_fn: 97.0000 - val_accuracy: 0.7321 - val_precision: 0.4418 - val_recall: 0.6940 - val_auc: 0.7858 - val_prc: 0.4990
Epoch 16/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5860 - tp: 404.9298 - fp: 658.6140 - tn: 1660.9825 - fn: 173.7193 - accuracy: 0.7067 - precision: 0.3780 - recall: 0.6875 - auc: 0.7645 - prc: 0.4562 - val_loss: 0.5713 - val_tp: 223.0000 - val_fp: 276.0000 - val_tn: 807.0000 - val_fn: 94.0000 - val_accuracy: 0.7357 - val_precision: 0.4469 - val_recall: 0.7035 - val_auc: 0.7883 - val_prc: 0.5039
Epoch 17/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5711 - tp: 416.5088 - fp: 660.7193 - tn: 1659.7018 - fn: 161.3158 - accuracy: 0.7149 - precision: 0.3900 - recall: 0.7235 - auc: 0.7793 - prc: 0.4818 - val_loss: 0.5680 - val_tp: 226.0000 - val_fp: 277.0000 - val_tn: 806.0000 - val_fn: 91.0000 - val_accuracy: 0.7371 - val_precision: 0.4493 - val_recall: 0.7129 - val_auc: 0.7907 - val_prc: 0.5097
Epoch 18/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5690 - tp: 402.3860 - fp: 629.8947 - tn: 1693.3333 - fn: 172.6316 - accuracy: 0.7231 - precision: 0.3891 - recall: 0.6958 - auc: 0.7761 - prc: 0.4940 - val_loss: 0.5639 - val_tp: 226.0000 - val_fp: 277.0000 - val_tn: 806.0000 - val_fn: 91.0000 - val_accuracy: 0.7371 - val_precision: 0.4493 - val_recall: 0.7129 - val_auc: 0.7932 - val_prc: 0.5149
Epoch 19/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5831 - tp: 419.7719 - fp: 617.3684 - tn: 1690.4211 - fn: 170.6842 - accuracy: 0.7236 - precision: 0.4058 - recall: 0.7034 - auc: 0.7725 - prc: 0.4969 - val_loss: 0.5599 - val_tp: 224.0000 - val_fp: 272.0000 - val_tn: 811.0000 - val_fn: 93.0000 - val_accuracy: 0.7393 - val_precision: 0.4516 - val_recall: 0.7066 - val_auc: 0.7951 - val_prc: 0.5218
Epoch 20/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5658 - tp: 397.3333 - fp: 610.8596 - tn: 1707.9298 - fn: 182.1228 - accuracy: 0.7256 - precision: 0.3980 - recall: 0.6944 - auc: 0.7798 - prc: 0.4945 - val_loss: 0.5534 - val_tp: 224.0000 - val_fp: 254.0000 - val_tn: 829.0000 - val_fn: 93.0000 - val_accuracy: 0.7521 - val_precision: 0.4686 - val_recall: 0.7066 - val_auc: 0.7973 - val_prc: 0.5272
Epoch 21/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5564 - tp: 393.0526 - fp: 604.2807 - tn: 1729.8947 - fn: 171.0175 - accuracy: 0.7364 - precision: 0.3967 - recall: 0.7035 - auc: 0.7829 - prc: 0.4830 - val_loss: 0.5584 - val_tp: 229.0000 - val_fp: 270.0000 - val_tn: 813.0000 - val_fn: 88.0000 - val_accuracy: 0.7443 - val_precision: 0.4589 - val_recall: 0.7224 - val_auc: 0.8007 - val_prc: 0.5303
Epoch 22/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5572 - tp: 400.0000 - fp: 635.5614 - tn: 1691.8772 - fn: 170.8070 - accuracy: 0.7173 - precision: 0.3824 - recall: 0.7055 - auc: 0.7855 - prc: 0.4816 - val_loss: 0.5545 - val_tp: 228.0000 - val_fp: 271.0000 - val_tn: 812.0000 - val_fn: 89.0000 - val_accuracy: 0.7429 - val_precision: 0.4569 - val_recall: 0.7192 - val_auc: 0.8028 - val_prc: 0.5360
Epoch 23/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5489 - tp: 378.8421 - fp: 610.8421 - tn: 1732.0351 - fn: 176.5263 - accuracy: 0.7219 - precision: 0.3716 - recall: 0.6728 - auc: 0.7804 - prc: 0.4915 - val_loss: 0.5520 - val_tp: 225.0000 - val_fp: 266.0000 - val_tn: 817.0000 - val_fn: 92.0000 - val_accuracy: 0.7443 - val_precision: 0.4582 - val_recall: 0.7098 - val_auc: 0.8051 - val_prc: 0.5411
Epoch 24/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5589 - tp: 405.0526 - fp: 584.5088 - tn: 1738.9298 - fn: 169.7544 - accuracy: 0.7401 - precision: 0.4045 - recall: 0.6918 - auc: 0.7856 - prc: 0.4823 - val_loss: 0.5435 - val_tp: 225.0000 - val_fp: 252.0000 - val_tn: 831.0000 - val_fn: 92.0000 - val_accuracy: 0.7543 - val_precision: 0.4717 - val_recall: 0.7098 - val_auc: 0.8069 - val_prc: 0.5511
Epoch 25/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5487 - tp: 411.5614 - fp: 573.3158 - tn: 1752.6842 - fn: 160.6842 - accuracy: 0.7465 - precision: 0.4204 - recall: 0.7218 - auc: 0.7987 - prc: 0.5258 - val_loss: 0.5428 - val_tp: 226.0000 - val_fp: 250.0000 - val_tn: 833.0000 - val_fn: 91.0000 - val_accuracy: 0.7564 - val_precision: 0.4748 - val_recall: 0.7129 - val_auc: 0.8084 - val_prc: 0.5518
Epoch 26/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5483 - tp: 396.6316 - fp: 601.6140 - tn: 1729.0702 - fn: 170.9298 - accuracy: 0.7315 - precision: 0.3963 - recall: 0.7003 - auc: 0.7929 - prc: 0.4989 - val_loss: 0.5411 - val_tp: 225.0000 - val_fp: 255.0000 - val_tn: 828.0000 - val_fn: 92.0000 - val_accuracy: 0.7521 - val_precision: 0.4688 - val_recall: 0.7098 - val_auc: 0.8098 - val_prc: 0.5558
Epoch 27/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5562 - tp: 405.7018 - fp: 586.2281 - tn: 1738.7544 - fn: 167.5614 - accuracy: 0.7381 - precision: 0.4125 - recall: 0.7124 - auc: 0.7923 - prc: 0.5155 - val_loss: 0.5363 - val_tp: 224.0000 - val_fp: 245.0000 - val_tn: 838.0000 - val_fn: 93.0000 - val_accuracy: 0.7586 - val_precision: 0.4776 - val_recall: 0.7066 - val_auc: 0.8113 - val_prc: 0.5597
Epoch 28/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5473 - tp: 378.3333 - fp: 570.0702 - tn: 1772.6667 - fn: 177.1754 - accuracy: 0.7409 - precision: 0.3920 - recall: 0.6761 - auc: 0.7844 - prc: 0.4887 - val_loss: 0.5323 - val_tp: 224.0000 - val_fp: 243.0000 - val_tn: 840.0000 - val_fn: 93.0000 - val_accuracy: 0.7600 - val_precision: 0.4797 - val_recall: 0.7066 - val_auc: 0.8130 - val_prc: 0.5647
Epoch 29/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5494 - tp: 399.0526 - fp: 562.7193 - tn: 1769.8070 - fn: 166.6667 - accuracy: 0.7526 - precision: 0.4202 - recall: 0.7042 - auc: 0.7904 - prc: 0.5069 - val_loss: 0.5359 - val_tp: 229.0000 - val_fp: 247.0000 - val_tn: 836.0000 - val_fn: 88.0000 - val_accuracy: 0.7607 - val_precision: 0.4811 - val_recall: 0.7224 - val_auc: 0.8154 - val_prc: 0.5726
Epoch 30/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5526 - tp: 404.8596 - fp: 573.5439 - tn: 1757.4386 - fn: 162.4035 - accuracy: 0.7420 - precision: 0.4092 - recall: 0.7165 - auc: 0.7904 - prc: 0.4923 - val_loss: 0.5299 - val_tp: 227.0000 - val_fp: 242.0000 - val_tn: 841.0000 - val_fn: 90.0000 - val_accuracy: 0.7629 - val_precision: 0.4840 - val_recall: 0.7161 - val_auc: 0.8158 - val_prc: 0.5751
Epoch 31/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5540 - tp: 392.7193 - fp: 555.2105 - tn: 1766.3684 - fn: 183.9474 - accuracy: 0.7394 - precision: 0.4107 - recall: 0.6779 - auc: 0.7951 - prc: 0.5171 - val_loss: 0.5313 - val_tp: 229.0000 - val_fp: 240.0000 - val_tn: 843.0000 - val_fn: 88.0000 - val_accuracy: 0.7657 - val_precision: 0.4883 - val_recall: 0.7224 - val_auc: 0.8163 - val_prc: 0.5758
Epoch 32/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5424 - tp: 400.7018 - fp: 552.6140 - tn: 1776.5439 - fn: 168.3860 - accuracy: 0.7477 - precision: 0.4094 - recall: 0.7085 - auc: 0.7958 - prc: 0.4871 - val_loss: 0.5285 - val_tp: 229.0000 - val_fp: 238.0000 - val_tn: 845.0000 - val_fn: 88.0000 - val_accuracy: 0.7671 - val_precision: 0.4904 - val_recall: 0.7224 - val_auc: 0.8168 - val_prc: 0.5769
Epoch 33/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5376 - tp: 403.5439 - fp: 559.4035 - tn: 1766.2632 - fn: 169.0351 - accuracy: 0.7534 - precision: 0.4184 - recall: 0.7135 - auc: 0.8040 - prc: 0.5170 - val_loss: 0.5243 - val_tp: 227.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 90.0000 - val_accuracy: 0.7679 - val_precision: 0.4913 - val_recall: 0.7161 - val_auc: 0.8180 - val_prc: 0.5826
Epoch 34/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5310 - tp: 401.2982 - fp: 514.0000 - tn: 1809.8421 - fn: 173.1053 - accuracy: 0.7687 - precision: 0.4492 - recall: 0.7052 - auc: 0.8126 - prc: 0.5542 - val_loss: 0.5217 - val_tp: 224.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 93.0000 - val_accuracy: 0.7657 - val_precision: 0.4880 - val_recall: 0.7066 - val_auc: 0.8189 - val_prc: 0.5827
Epoch 35/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5468 - tp: 407.0526 - fp: 549.0000 - tn: 1773.6667 - fn: 168.5263 - accuracy: 0.7496 - precision: 0.4280 - recall: 0.7119 - auc: 0.7947 - prc: 0.5560 - val_loss: 0.5245 - val_tp: 224.0000 - val_fp: 237.0000 - val_tn: 846.0000 - val_fn: 93.0000 - val_accuracy: 0.7643 - val_precision: 0.4859 - val_recall: 0.7066 - val_auc: 0.8203 - val_prc: 0.5861
Epoch 36/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5285 - tp: 399.6842 - fp: 507.3158 - tn: 1816.0175 - fn: 175.2281 - accuracy: 0.7682 - precision: 0.4466 - recall: 0.6916 - auc: 0.8123 - prc: 0.5545 - val_loss: 0.5182 - val_tp: 222.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 95.0000 - val_accuracy: 0.7650 - val_precision: 0.4868 - val_recall: 0.7003 - val_auc: 0.8210 - val_prc: 0.5911
Epoch 37/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5411 - tp: 407.1930 - fp: 525.5263 - tn: 1798.3860 - fn: 167.1404 - accuracy: 0.7589 - precision: 0.4359 - recall: 0.7165 - auc: 0.7983 - prc: 0.5397 - val_loss: 0.5157 - val_tp: 221.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 96.0000 - val_accuracy: 0.7657 - val_precision: 0.4879 - val_recall: 0.6972 - val_auc: 0.8218 - val_prc: 0.5956
Epoch 38/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5332 - tp: 384.5263 - fp: 524.8421 - tn: 1814.2281 - fn: 174.6491 - accuracy: 0.7579 - precision: 0.4278 - recall: 0.6878 - auc: 0.8055 - prc: 0.5301 - val_loss: 0.5159 - val_tp: 222.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 95.0000 - val_accuracy: 0.7650 - val_precision: 0.4868 - val_recall: 0.7003 - val_auc: 0.8223 - val_prc: 0.5973
Epoch 39/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5212 - tp: 410.4912 - fp: 546.1228 - tn: 1781.1754 - fn: 160.4561 - accuracy: 0.7544 - precision: 0.4187 - recall: 0.7250 - auc: 0.8121 - prc: 0.5423 - val_loss: 0.5180 - val_tp: 225.0000 - val_fp: 237.0000 - val_tn: 846.0000 - val_fn: 92.0000 - val_accuracy: 0.7650 - val_precision: 0.4870 - val_recall: 0.7098 - val_auc: 0.8234 - val_prc: 0.6004
Epoch 40/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5283 - tp: 403.5439 - fp: 539.7544 - tn: 1784.0351 - fn: 170.9123 - accuracy: 0.7558 - precision: 0.4359 - recall: 0.7121 - auc: 0.8157 - prc: 0.5552 - val_loss: 0.5119 - val_tp: 221.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 96.0000 - val_accuracy: 0.7679 - val_precision: 0.4911 - val_recall: 0.6972 - val_auc: 0.8241 - val_prc: 0.6041
Epoch 41/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5323 - tp: 403.5263 - fp: 511.5088 - tn: 1809.8070 - fn: 173.4035 - accuracy: 0.7625 - precision: 0.4356 - recall: 0.6996 - auc: 0.8065 - prc: 0.5514 - val_loss: 0.5137 - val_tp: 223.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 94.0000 - val_accuracy: 0.7679 - val_precision: 0.4912 - val_recall: 0.7035 - val_auc: 0.8254 - val_prc: 0.6059
Epoch 42/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5293 - tp: 388.8947 - fp: 509.3158 - tn: 1815.0702 - fn: 184.9649 - accuracy: 0.7618 - precision: 0.4322 - recall: 0.6791 - auc: 0.8092 - prc: 0.5389 - val_loss: 0.5081 - val_tp: 221.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 96.0000 - val_accuracy: 0.7707 - val_precision: 0.4955 - val_recall: 0.6972 - val_auc: 0.8253 - val_prc: 0.6081
Epoch 43/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5273 - tp: 411.6491 - fp: 514.8246 - tn: 1800.7018 - fn: 171.0702 - accuracy: 0.7612 - precision: 0.4399 - recall: 0.6996 - auc: 0.8127 - prc: 0.5618 - val_loss: 0.5061 - val_tp: 221.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 96.0000 - val_accuracy: 0.7721 - val_precision: 0.4977 - val_recall: 0.6972 - val_auc: 0.8258 - val_prc: 0.6116
Epoch 44/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5238 - tp: 400.8421 - fp: 513.4386 - tn: 1812.0351 - fn: 171.9298 - accuracy: 0.7656 - precision: 0.4454 - recall: 0.7006 - auc: 0.8172 - prc: 0.5806 - val_loss: 0.5053 - val_tp: 220.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 97.0000 - val_accuracy: 0.7721 - val_precision: 0.4977 - val_recall: 0.6940 - val_auc: 0.8259 - val_prc: 0.6120
Epoch 45/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5197 - tp: 387.3684 - fp: 505.6316 - tn: 1829.5614 - fn: 175.6842 - accuracy: 0.7647 - precision: 0.4280 - recall: 0.6791 - auc: 0.8119 - prc: 0.5581 - val_loss: 0.5073 - val_tp: 220.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 97.0000 - val_accuracy: 0.7686 - val_precision: 0.4922 - val_recall: 0.6940 - val_auc: 0.8264 - val_prc: 0.6156
Epoch 46/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5209 - tp: 387.2456 - fp: 487.0526 - tn: 1846.7544 - fn: 177.1930 - accuracy: 0.7692 - precision: 0.4332 - recall: 0.6782 - auc: 0.8113 - prc: 0.5483 - val_loss: 0.5098 - val_tp: 221.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 96.0000 - val_accuracy: 0.7664 - val_precision: 0.4889 - val_recall: 0.6972 - val_auc: 0.8269 - val_prc: 0.6181
Epoch 47/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5405 - tp: 385.4737 - fp: 513.6491 - tn: 1808.4737 - fn: 190.6491 - accuracy: 0.7568 - precision: 0.4223 - recall: 0.6635 - auc: 0.8003 - prc: 0.5251 - val_loss: 0.5080 - val_tp: 220.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 97.0000 - val_accuracy: 0.7671 - val_precision: 0.4900 - val_recall: 0.6940 - val_auc: 0.8276 - val_prc: 0.6171
Epoch 48/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5345 - tp: 403.0351 - fp: 509.9649 - tn: 1803.7193 - fn: 181.5263 - accuracy: 0.7626 - precision: 0.4505 - recall: 0.6993 - auc: 0.8134 - prc: 0.5703 - val_loss: 0.5012 - val_tp: 219.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 98.0000 - val_accuracy: 0.7750 - val_precision: 0.5023 - val_recall: 0.6909 - val_auc: 0.8289 - val_prc: 0.6217
Epoch 49/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5295 - tp: 385.7719 - fp: 476.2982 - tn: 1854.7719 - fn: 181.4035 - accuracy: 0.7705 - precision: 0.4389 - recall: 0.6763 - auc: 0.8054 - prc: 0.5435 - val_loss: 0.4997 - val_tp: 219.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 98.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.6909 - val_auc: 0.8294 - val_prc: 0.6206
Epoch 50/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5171 - tp: 400.8947 - fp: 482.4035 - tn: 1839.5614 - fn: 175.3860 - accuracy: 0.7708 - precision: 0.4465 - recall: 0.6920 - auc: 0.8176 - prc: 0.5776 - val_loss: 0.5011 - val_tp: 219.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 98.0000 - val_accuracy: 0.7700 - val_precision: 0.4944 - val_recall: 0.6909 - val_auc: 0.8288 - val_prc: 0.6211
Epoch 51/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5347 - tp: 391.5439 - fp: 492.0000 - tn: 1824.9825 - fn: 189.7193 - accuracy: 0.7610 - precision: 0.4398 - recall: 0.6748 - auc: 0.8082 - prc: 0.5478 - val_loss: 0.4994 - val_tp: 220.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 97.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.6940 - val_auc: 0.8296 - val_prc: 0.6255
Epoch 52/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5119 - tp: 375.9825 - fp: 466.9825 - tn: 1877.5263 - fn: 177.7544 - accuracy: 0.7746 - precision: 0.4329 - recall: 0.6680 - auc: 0.8195 - prc: 0.5315 - val_loss: 0.4977 - val_tp: 218.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 99.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.6877 - val_auc: 0.8305 - val_prc: 0.6272
Epoch 53/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5194 - tp: 404.5789 - fp: 494.0877 - tn: 1827.2807 - fn: 172.2982 - accuracy: 0.7672 - precision: 0.4455 - recall: 0.7006 - auc: 0.8218 - prc: 0.5510 - val_loss: 0.5035 - val_tp: 219.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 98.0000 - val_accuracy: 0.7707 - val_precision: 0.4955 - val_recall: 0.6909 - val_auc: 0.8306 - val_prc: 0.6256
Epoch 54/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5207 - tp: 415.4912 - fp: 483.1053 - tn: 1831.1053 - fn: 168.5439 - accuracy: 0.7745 - precision: 0.4654 - recall: 0.7133 - auc: 0.8215 - prc: 0.5881 - val_loss: 0.4943 - val_tp: 218.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 99.0000 - val_accuracy: 0.7786 - val_precision: 0.5082 - val_recall: 0.6877 - val_auc: 0.8312 - val_prc: 0.6284
Epoch 55/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5228 - tp: 390.6140 - fp: 462.7719 - tn: 1861.8070 - fn: 183.0526 - accuracy: 0.7796 - precision: 0.4562 - recall: 0.6724 - auc: 0.8157 - prc: 0.5497 - val_loss: 0.4946 - val_tp: 218.0000 - val_fp: 216.0000 - val_tn: 867.0000 - val_fn: 99.0000 - val_accuracy: 0.7750 - val_precision: 0.5023 - val_recall: 0.6877 - val_auc: 0.8312 - val_prc: 0.6310
Epoch 56/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5135 - tp: 391.1930 - fp: 473.9123 - tn: 1857.0000 - fn: 176.1404 - accuracy: 0.7805 - precision: 0.4544 - recall: 0.6985 - auc: 0.8215 - prc: 0.5723 - val_loss: 0.4971 - val_tp: 217.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 100.0000 - val_accuracy: 0.7721 - val_precision: 0.4977 - val_recall: 0.6845 - val_auc: 0.8318 - val_prc: 0.6333
Epoch 57/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5156 - tp: 385.4386 - fp: 497.1053 - tn: 1835.4035 - fn: 180.2982 - accuracy: 0.7692 - precision: 0.4392 - recall: 0.6914 - auc: 0.8188 - prc: 0.5700 - val_loss: 0.4965 - val_tp: 218.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 99.0000 - val_accuracy: 0.7729 - val_precision: 0.4989 - val_recall: 0.6877 - val_auc: 0.8325 - val_prc: 0.6345
Epoch 58/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5133 - tp: 386.7544 - fp: 492.8772 - tn: 1842.5439 - fn: 176.0702 - accuracy: 0.7672 - precision: 0.4389 - recall: 0.6845 - auc: 0.8184 - prc: 0.5824 - val_loss: 0.4974 - val_tp: 219.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 98.0000 - val_accuracy: 0.7729 - val_precision: 0.4989 - val_recall: 0.6909 - val_auc: 0.8329 - val_prc: 0.6372
Epoch 59/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5137 - tp: 408.2456 - fp: 502.0351 - tn: 1813.5088 - fn: 174.4561 - accuracy: 0.7701 - precision: 0.4530 - recall: 0.7036 - auc: 0.8260 - prc: 0.5918 - val_loss: 0.4964 - val_tp: 220.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 97.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.6940 - val_auc: 0.8329 - val_prc: 0.6386
Epoch 60/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5113 - tp: 389.7193 - fp: 470.7368 - tn: 1864.4035 - fn: 173.3860 - accuracy: 0.7761 - precision: 0.4475 - recall: 0.6990 - auc: 0.8234 - prc: 0.5783 - val_loss: 0.4937 - val_tp: 217.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 100.0000 - val_accuracy: 0.7771 - val_precision: 0.5058 - val_recall: 0.6845 - val_auc: 0.8335 - val_prc: 0.6390
Epoch 61/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5258 - tp: 391.6491 - fp: 495.6316 - tn: 1820.7719 - fn: 190.1930 - accuracy: 0.7686 - precision: 0.4469 - recall: 0.6719 - auc: 0.8168 - prc: 0.5600 - val_loss: 0.4928 - val_tp: 215.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 102.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.6782 - val_auc: 0.8334 - val_prc: 0.6404
Epoch 62/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5104 - tp: 389.5614 - fp: 479.4211 - tn: 1853.8772 - fn: 175.3860 - accuracy: 0.7703 - precision: 0.4357 - recall: 0.6874 - auc: 0.8211 - prc: 0.5526 - val_loss: 0.4906 - val_tp: 215.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 102.0000 - val_accuracy: 0.7757 - val_precision: 0.5035 - val_recall: 0.6782 - val_auc: 0.8332 - val_prc: 0.6406
Epoch 63/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5088 - tp: 399.4561 - fp: 466.8246 - tn: 1861.2456 - fn: 170.7193 - accuracy: 0.7815 - precision: 0.4577 - recall: 0.6961 - auc: 0.8277 - prc: 0.5691 - val_loss: 0.4896 - val_tp: 217.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 100.0000 - val_accuracy: 0.7771 - val_precision: 0.5058 - val_recall: 0.6845 - val_auc: 0.8336 - val_prc: 0.6405
Epoch 64/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5266 - tp: 393.5965 - fp: 479.6140 - tn: 1841.7544 - fn: 183.2807 - accuracy: 0.7694 - precision: 0.4529 - recall: 0.6788 - auc: 0.8158 - prc: 0.5779 - val_loss: 0.4929 - val_tp: 219.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 98.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.6909 - val_auc: 0.8341 - val_prc: 0.6388
Epoch 65/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5362 - tp: 396.3509 - fp: 458.3333 - tn: 1859.2632 - fn: 184.2982 - accuracy: 0.7798 - precision: 0.4653 - recall: 0.6855 - auc: 0.8121 - prc: 0.5431 - val_loss: 0.4898 - val_tp: 214.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 103.0000 - val_accuracy: 0.7743 - val_precision: 0.5012 - val_recall: 0.6751 - val_auc: 0.8342 - val_prc: 0.6414
Epoch 66/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5207 - tp: 386.7544 - fp: 470.8947 - tn: 1854.8947 - fn: 185.7018 - accuracy: 0.7686 - precision: 0.4438 - recall: 0.6774 - auc: 0.8160 - prc: 0.5723 - val_loss: 0.4970 - val_tp: 220.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 97.0000 - val_accuracy: 0.7707 - val_precision: 0.4955 - val_recall: 0.6940 - val_auc: 0.8344 - val_prc: 0.6447
Epoch 67/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5123 - tp: 394.7193 - fp: 486.2807 - tn: 1845.4737 - fn: 171.7719 - accuracy: 0.7713 - precision: 0.4497 - recall: 0.6962 - auc: 0.8254 - prc: 0.5864 - val_loss: 0.4910 - val_tp: 216.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 101.0000 - val_accuracy: 0.7743 - val_precision: 0.5012 - val_recall: 0.6814 - val_auc: 0.8348 - val_prc: 0.6467
Epoch 68/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5257 - tp: 397.0877 - fp: 482.3333 - tn: 1840.9825 - fn: 177.8421 - accuracy: 0.7694 - precision: 0.4544 - recall: 0.6953 - auc: 0.8170 - prc: 0.5662 - val_loss: 0.4859 - val_tp: 213.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 104.0000 - val_accuracy: 0.7771 - val_precision: 0.5059 - val_recall: 0.6719 - val_auc: 0.8354 - val_prc: 0.6471
Epoch 69/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5191 - tp: 413.7018 - fp: 481.5789 - tn: 1827.8070 - fn: 175.1579 - accuracy: 0.7697 - precision: 0.4547 - recall: 0.6963 - auc: 0.8199 - prc: 0.5928 - val_loss: 0.4880 - val_tp: 213.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 104.0000 - val_accuracy: 0.7707 - val_precision: 0.4953 - val_recall: 0.6719 - val_auc: 0.8347 - val_prc: 0.6442
Epoch 70/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5150 - tp: 395.6842 - fp: 468.5088 - tn: 1851.7895 - fn: 182.2632 - accuracy: 0.7779 - precision: 0.4636 - recall: 0.6757 - auc: 0.8255 - prc: 0.5834 - val_loss: 0.4879 - val_tp: 215.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 102.0000 - val_accuracy: 0.7750 - val_precision: 0.5023 - val_recall: 0.6782 - val_auc: 0.8347 - val_prc: 0.6471
Epoch 71/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5122 - tp: 379.8947 - fp: 449.6667 - tn: 1883.7719 - fn: 184.9123 - accuracy: 0.7816 - precision: 0.4571 - recall: 0.6638 - auc: 0.8147 - prc: 0.5884 - val_loss: 0.4929 - val_tp: 218.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 99.0000 - val_accuracy: 0.7707 - val_precision: 0.4955 - val_recall: 0.6877 - val_auc: 0.8348 - val_prc: 0.6451
Epoch 72/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5266 - tp: 401.1053 - fp: 483.4737 - tn: 1832.8772 - fn: 180.7895 - accuracy: 0.7660 - precision: 0.4495 - recall: 0.6914 - auc: 0.8165 - prc: 0.5623 - val_loss: 0.4901 - val_tp: 216.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 101.0000 - val_accuracy: 0.7714 - val_precision: 0.4966 - val_recall: 0.6814 - val_auc: 0.8356 - val_prc: 0.6470
Epoch 73/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4934 - tp: 384.8246 - fp: 450.0000 - tn: 1885.3158 - fn: 178.1053 - accuracy: 0.7905 - precision: 0.4684 - recall: 0.7033 - auc: 0.8346 - prc: 0.6048 - val_loss: 0.4852 - val_tp: 216.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 101.0000 - val_accuracy: 0.7764 - val_precision: 0.5047 - val_recall: 0.6814 - val_auc: 0.8357 - val_prc: 0.6500
Epoch 74/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5208 - tp: 392.9474 - fp: 465.5614 - tn: 1864.2982 - fn: 175.4386 - accuracy: 0.7763 - precision: 0.4520 - recall: 0.6915 - auc: 0.8110 - prc: 0.5692 - val_loss: 0.4878 - val_tp: 218.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 99.0000 - val_accuracy: 0.7757 - val_precision: 0.5035 - val_recall: 0.6877 - val_auc: 0.8357 - val_prc: 0.6487
Epoch 75/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4899 - tp: 408.0702 - fp: 447.0877 - tn: 1877.4035 - fn: 165.6842 - accuracy: 0.7956 - precision: 0.4871 - recall: 0.7249 - auc: 0.8418 - prc: 0.6282 - val_loss: 0.4901 - val_tp: 218.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 99.0000 - val_accuracy: 0.7729 - val_precision: 0.4989 - val_recall: 0.6877 - val_auc: 0.8359 - val_prc: 0.6506
Epoch 76/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5006 - tp: 396.7895 - fp: 452.9649 - tn: 1879.2281 - fn: 169.2632 - accuracy: 0.7876 - precision: 0.4741 - recall: 0.7007 - auc: 0.8342 - prc: 0.5929 - val_loss: 0.4859 - val_tp: 219.0000 - val_fp: 216.0000 - val_tn: 867.0000 - val_fn: 98.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.6909 - val_auc: 0.8355 - val_prc: 0.6514
Epoch 77/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5128 - tp: 391.4737 - fp: 482.4912 - tn: 1850.0877 - fn: 174.1930 - accuracy: 0.7726 - precision: 0.4427 - recall: 0.6797 - auc: 0.8188 - prc: 0.5721 - val_loss: 0.4903 - val_tp: 222.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 95.0000 - val_accuracy: 0.7721 - val_precision: 0.4978 - val_recall: 0.7003 - val_auc: 0.8361 - val_prc: 0.6516
Epoch 78/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5022 - tp: 407.9825 - fp: 465.7544 - tn: 1861.9123 - fn: 162.5965 - accuracy: 0.7859 - precision: 0.4668 - recall: 0.7165 - auc: 0.8300 - prc: 0.5954 - val_loss: 0.4892 - val_tp: 220.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 97.0000 - val_accuracy: 0.7721 - val_precision: 0.4977 - val_recall: 0.6940 - val_auc: 0.8365 - val_prc: 0.6525
Epoch 79/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5181 - tp: 404.6491 - fp: 470.4035 - tn: 1847.9825 - fn: 175.2105 - accuracy: 0.7773 - precision: 0.4651 - recall: 0.6981 - auc: 0.8215 - prc: 0.5871 - val_loss: 0.4807 - val_tp: 216.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 101.0000 - val_accuracy: 0.7771 - val_precision: 0.5059 - val_recall: 0.6814 - val_auc: 0.8372 - val_prc: 0.6558
Epoch 80/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5104 - tp: 398.5614 - fp: 449.1754 - tn: 1880.0000 - fn: 170.5088 - accuracy: 0.7856 - precision: 0.4658 - recall: 0.7017 - auc: 0.8229 - prc: 0.5881 - val_loss: 0.4825 - val_tp: 219.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 98.0000 - val_accuracy: 0.7764 - val_precision: 0.5046 - val_recall: 0.6909 - val_auc: 0.8374 - val_prc: 0.6579
Epoch 81/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5149 - tp: 403.0351 - fp: 472.1228 - tn: 1850.2982 - fn: 172.7895 - accuracy: 0.7788 - precision: 0.4714 - recall: 0.7056 - auc: 0.8274 - prc: 0.5905 - val_loss: 0.4862 - val_tp: 221.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 96.0000 - val_accuracy: 0.7750 - val_precision: 0.5023 - val_recall: 0.6972 - val_auc: 0.8374 - val_prc: 0.6582
Epoch 82/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5169 - tp: 376.3684 - fp: 457.8246 - tn: 1881.6316 - fn: 182.4211 - accuracy: 0.7777 - precision: 0.4461 - recall: 0.6762 - auc: 0.8145 - prc: 0.5628 - val_loss: 0.4847 - val_tp: 219.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 98.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.6909 - val_auc: 0.8379 - val_prc: 0.6594
Epoch 83/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5128 - tp: 413.6316 - fp: 482.0000 - tn: 1833.9123 - fn: 168.7018 - accuracy: 0.7743 - precision: 0.4675 - recall: 0.7132 - auc: 0.8275 - prc: 0.6127 - val_loss: 0.4837 - val_tp: 219.0000 - val_fp: 216.0000 - val_tn: 867.0000 - val_fn: 98.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.6909 - val_auc: 0.8384 - val_prc: 0.6599
Epoch 84/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5138 - tp: 396.3684 - fp: 469.0702 - tn: 1852.5789 - fn: 180.2281 - accuracy: 0.7778 - precision: 0.4534 - recall: 0.6987 - auc: 0.8224 - prc: 0.5793 - val_loss: 0.4906 - val_tp: 221.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 96.0000 - val_accuracy: 0.7714 - val_precision: 0.4966 - val_recall: 0.6972 - val_auc: 0.8377 - val_prc: 0.6576
Epoch 85/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5023 - tp: 392.0000 - fp: 457.7368 - tn: 1877.0175 - fn: 171.4912 - accuracy: 0.7848 - precision: 0.4596 - recall: 0.7077 - auc: 0.8306 - prc: 0.5894 - val_loss: 0.4875 - val_tp: 220.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 97.0000 - val_accuracy: 0.7714 - val_precision: 0.4966 - val_recall: 0.6940 - val_auc: 0.8383 - val_prc: 0.6595
Epoch 86/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5021 - tp: 413.9123 - fp: 478.6140 - tn: 1845.2456 - fn: 160.4737 - accuracy: 0.7782 - precision: 0.4608 - recall: 0.7269 - auc: 0.8325 - prc: 0.6011 - val_loss: 0.4867 - val_tp: 220.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 97.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.6940 - val_auc: 0.8382 - val_prc: 0.6595
Epoch 87/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5111 - tp: 392.8772 - fp: 457.8596 - tn: 1869.5614 - fn: 177.9474 - accuracy: 0.7788 - precision: 0.4577 - recall: 0.6898 - auc: 0.8215 - prc: 0.5829 - val_loss: 0.4765 - val_tp: 218.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 99.0000 - val_accuracy: 0.7807 - val_precision: 0.5117 - val_recall: 0.6877 - val_auc: 0.8390 - val_prc: 0.6612
Epoch 88/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5164 - tp: 398.1404 - fp: 443.6667 - tn: 1875.4737 - fn: 180.9649 - accuracy: 0.7842 - precision: 0.4782 - recall: 0.6883 - auc: 0.8253 - prc: 0.5946 - val_loss: 0.4801 - val_tp: 219.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 98.0000 - val_accuracy: 0.7771 - val_precision: 0.5058 - val_recall: 0.6909 - val_auc: 0.8393 - val_prc: 0.6627
Epoch 89/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5193 - tp: 377.3158 - fp: 468.8421 - tn: 1860.4912 - fn: 191.5965 - accuracy: 0.7736 - precision: 0.4428 - recall: 0.6558 - auc: 0.8120 - prc: 0.5786 - val_loss: 0.4832 - val_tp: 219.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 98.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.6909 - val_auc: 0.8387 - val_prc: 0.6631
Epoch 90/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5243 - tp: 410.0526 - fp: 466.8947 - tn: 1848.7544 - fn: 172.5439 - accuracy: 0.7801 - precision: 0.4676 - recall: 0.6993 - auc: 0.8179 - prc: 0.5836 - val_loss: 0.4832 - val_tp: 219.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 98.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.6909 - val_auc: 0.8388 - val_prc: 0.6618
Epoch 91/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5158 - tp: 402.7193 - fp: 454.4912 - tn: 1861.0175 - fn: 180.0175 - accuracy: 0.7807 - precision: 0.4645 - recall: 0.6853 - auc: 0.8240 - prc: 0.5640 - val_loss: 0.4804 - val_tp: 219.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 98.0000 - val_accuracy: 0.7779 - val_precision: 0.5069 - val_recall: 0.6909 - val_auc: 0.8393 - val_prc: 0.6633
Epoch 92/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5161 - tp: 387.1579 - fp: 448.3684 - tn: 1878.9825 - fn: 183.7368 - accuracy: 0.7827 - precision: 0.4654 - recall: 0.6838 - auc: 0.8211 - prc: 0.5811 - val_loss: 0.4847 - val_tp: 220.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 97.0000 - val_accuracy: 0.7750 - val_precision: 0.5023 - val_recall: 0.6940 - val_auc: 0.8394 - val_prc: 0.6636
Epoch 93/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5409 - tp: 394.1228 - fp: 463.5614 - tn: 1851.1404 - fn: 189.4211 - accuracy: 0.7716 - precision: 0.4597 - recall: 0.6694 - auc: 0.8080 - prc: 0.5570 - val_loss: 0.4840 - val_tp: 220.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 97.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.6940 - val_auc: 0.8397 - val_prc: 0.6641
Epoch 94/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5107 - tp: 395.8596 - fp: 470.7018 - tn: 1853.6316 - fn: 178.0526 - accuracy: 0.7769 - precision: 0.4580 - recall: 0.6974 - auc: 0.8237 - prc: 0.5943 - val_loss: 0.4804 - val_tp: 219.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 98.0000 - val_accuracy: 0.7764 - val_precision: 0.5046 - val_recall: 0.6909 - val_auc: 0.8399 - val_prc: 0.6643
Epoch 95/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4973 - tp: 398.1930 - fp: 466.5088 - tn: 1863.6491 - fn: 169.8947 - accuracy: 0.7833 - precision: 0.4572 - recall: 0.7110 - auc: 0.8338 - prc: 0.5865 - val_loss: 0.4817 - val_tp: 220.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 97.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.6940 - val_auc: 0.8401 - val_prc: 0.6660
Epoch 96/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5139 - tp: 386.8947 - fp: 460.9825 - tn: 1868.4386 - fn: 181.9298 - accuracy: 0.7799 - precision: 0.4485 - recall: 0.6723 - auc: 0.8140 - prc: 0.5640 - val_loss: 0.4869 - val_tp: 225.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 92.0000 - val_accuracy: 0.7750 - val_precision: 0.5022 - val_recall: 0.7098 - val_auc: 0.8398 - val_prc: 0.6659
Epoch 97/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4965 - tp: 405.7719 - fp: 448.1404 - tn: 1875.1754 - fn: 169.1579 - accuracy: 0.7926 - precision: 0.4844 - recall: 0.7107 - auc: 0.8361 - prc: 0.6262 - val_loss: 0.4835 - val_tp: 222.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 95.0000 - val_accuracy: 0.7786 - val_precision: 0.5080 - val_recall: 0.7003 - val_auc: 0.8401 - val_prc: 0.6670
Epoch 98/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4958 - tp: 402.9298 - fp: 441.3158 - tn: 1891.3509 - fn: 162.6491 - accuracy: 0.7915 - precision: 0.4636 - recall: 0.7053 - auc: 0.8283 - prc: 0.5949 - val_loss: 0.4792 - val_tp: 219.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 98.0000 - val_accuracy: 0.7779 - val_precision: 0.5069 - val_recall: 0.6909 - val_auc: 0.8400 - val_prc: 0.6648
Epoch 99/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4994 - tp: 399.8947 - fp: 450.8246 - tn: 1874.7368 - fn: 172.7895 - accuracy: 0.7895 - precision: 0.4738 - recall: 0.6952 - auc: 0.8316 - prc: 0.5999 - val_loss: 0.4781 - val_tp: 220.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 97.0000 - val_accuracy: 0.7807 - val_precision: 0.5116 - val_recall: 0.6940 - val_auc: 0.8402 - val_prc: 0.6643
Epoch 100/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5134 - tp: 392.6842 - fp: 460.3509 - tn: 1871.2982 - fn: 173.9123 - accuracy: 0.7807 - precision: 0.4511 - recall: 0.6836 - auc: 0.8170 - prc: 0.5676 - val_loss: 0.4839 - val_tp: 225.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 92.0000 - val_accuracy: 0.7779 - val_precision: 0.5068 - val_recall: 0.7098 - val_auc: 0.8401 - val_prc: 0.6641
Epoch 101/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5068 - tp: 397.8947 - fp: 465.3509 - tn: 1858.8772 - fn: 176.1228 - accuracy: 0.7782 - precision: 0.4594 - recall: 0.6945 - auc: 0.8292 - prc: 0.5888 - val_loss: 0.4788 - val_tp: 221.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 96.0000 - val_accuracy: 0.7814 - val_precision: 0.5128 - val_recall: 0.6972 - val_auc: 0.8401 - val_prc: 0.6659
Epoch 102/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5214 - tp: 402.6842 - fp: 452.2807 - tn: 1861.2807 - fn: 182.0000 - accuracy: 0.7812 - precision: 0.4812 - recall: 0.6884 - auc: 0.8261 - prc: 0.6075 - val_loss: 0.4744 - val_tp: 221.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 96.0000 - val_accuracy: 0.7829 - val_precision: 0.5152 - val_recall: 0.6972 - val_auc: 0.8404 - val_prc: 0.6668
Epoch 103/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5231 - tp: 389.4386 - fp: 458.5088 - tn: 1862.0000 - fn: 188.2982 - accuracy: 0.7766 - precision: 0.4638 - recall: 0.6647 - auc: 0.8199 - prc: 0.5880 - val_loss: 0.4772 - val_tp: 221.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 96.0000 - val_accuracy: 0.7800 - val_precision: 0.5104 - val_recall: 0.6972 - val_auc: 0.8401 - val_prc: 0.6649
Epoch 104/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5225 - tp: 387.7719 - fp: 449.6842 - tn: 1879.7018 - fn: 181.0877 - accuracy: 0.7814 - precision: 0.4560 - recall: 0.6867 - auc: 0.8160 - prc: 0.5504 - val_loss: 0.4821 - val_tp: 222.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 95.0000 - val_accuracy: 0.7793 - val_precision: 0.5092 - val_recall: 0.7003 - val_auc: 0.8396 - val_prc: 0.6661
Epoch 105/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5051 - tp: 393.8947 - fp: 478.8596 - tn: 1855.9474 - fn: 169.5439 - accuracy: 0.7778 - precision: 0.4496 - recall: 0.7004 - auc: 0.8271 - prc: 0.5707 - val_loss: 0.4811 - val_tp: 221.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 96.0000 - val_accuracy: 0.7800 - val_precision: 0.5104 - val_recall: 0.6972 - val_auc: 0.8403 - val_prc: 0.6678
Epoch 106/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5270 - tp: 394.0000 - fp: 456.2456 - tn: 1876.2632 - fn: 171.7368 - accuracy: 0.7808 - precision: 0.4572 - recall: 0.6756 - auc: 0.8097 - prc: 0.5591 - val_loss: 0.4861 - val_tp: 224.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 93.0000 - val_accuracy: 0.7771 - val_precision: 0.5056 - val_recall: 0.7066 - val_auc: 0.8397 - val_prc: 0.6665
Epoch 107/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5139 - tp: 402.8772 - fp: 490.4561 - tn: 1832.0351 - fn: 172.8772 - accuracy: 0.7732 - precision: 0.4610 - recall: 0.7115 - auc: 0.8234 - prc: 0.6012 - val_loss: 0.4819 - val_tp: 222.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 95.0000 - val_accuracy: 0.7793 - val_precision: 0.5092 - val_recall: 0.7003 - val_auc: 0.8408 - val_prc: 0.6703
Epoch 108/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5134 - tp: 408.5088 - fp: 466.5088 - tn: 1845.0000 - fn: 178.2281 - accuracy: 0.7746 - precision: 0.4585 - recall: 0.6887 - auc: 0.8233 - prc: 0.6032 - val_loss: 0.4824 - val_tp: 221.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 96.0000 - val_accuracy: 0.7786 - val_precision: 0.5080 - val_recall: 0.6972 - val_auc: 0.8409 - val_prc: 0.6695
Epoch 109/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5052 - tp: 401.7719 - fp: 460.1404 - tn: 1867.4035 - fn: 168.9298 - accuracy: 0.7846 - precision: 0.4731 - recall: 0.7194 - auc: 0.8295 - prc: 0.6125 - val_loss: 0.4856 - val_tp: 223.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 94.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.7035 - val_auc: 0.8403 - val_prc: 0.6682
Epoch 110/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5041 - tp: 405.6316 - fp: 473.5263 - tn: 1849.6667 - fn: 169.4211 - accuracy: 0.7800 - precision: 0.4656 - recall: 0.7103 - auc: 0.8313 - prc: 0.6232 - val_loss: 0.4841 - val_tp: 226.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 91.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7129 - val_auc: 0.8403 - val_prc: 0.6697
Epoch 111/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5191 - tp: 384.8070 - fp: 479.3509 - tn: 1855.9298 - fn: 178.1579 - accuracy: 0.7729 - precision: 0.4348 - recall: 0.6747 - auc: 0.8130 - prc: 0.5496 - val_loss: 0.4803 - val_tp: 220.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 97.0000 - val_accuracy: 0.7793 - val_precision: 0.5093 - val_recall: 0.6940 - val_auc: 0.8403 - val_prc: 0.6703
Epoch 112/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5016 - tp: 399.2982 - fp: 421.9474 - tn: 1905.6140 - fn: 171.3860 - accuracy: 0.7952 - precision: 0.4803 - recall: 0.6907 - auc: 0.8277 - prc: 0.5980 - val_loss: 0.4799 - val_tp: 220.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 97.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.6940 - val_auc: 0.8397 - val_prc: 0.6685
Epoch 113/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5081 - tp: 388.5439 - fp: 474.9474 - tn: 1854.8070 - fn: 179.9474 - accuracy: 0.7711 - precision: 0.4398 - recall: 0.6928 - auc: 0.8262 - prc: 0.5806 - val_loss: 0.4742 - val_tp: 216.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 101.0000 - val_accuracy: 0.7814 - val_precision: 0.5131 - val_recall: 0.6814 - val_auc: 0.8405 - val_prc: 0.6694
Epoch 114/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5002 - tp: 392.4912 - fp: 457.9123 - tn: 1874.7368 - fn: 173.1053 - accuracy: 0.7827 - precision: 0.4568 - recall: 0.7008 - auc: 0.8283 - prc: 0.5933 - val_loss: 0.4742 - val_tp: 217.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 100.0000 - val_accuracy: 0.7821 - val_precision: 0.5142 - val_recall: 0.6845 - val_auc: 0.8411 - val_prc: 0.6716
Epoch 115/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5146 - tp: 397.2456 - fp: 449.2982 - tn: 1873.6491 - fn: 178.0526 - accuracy: 0.7783 - precision: 0.4539 - recall: 0.6769 - auc: 0.8210 - prc: 0.5741 - val_loss: 0.4787 - val_tp: 224.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 93.0000 - val_accuracy: 0.7821 - val_precision: 0.5138 - val_recall: 0.7066 - val_auc: 0.8416 - val_prc: 0.6718
Epoch 116/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5031 - tp: 396.4386 - fp: 442.3684 - tn: 1884.5614 - fn: 174.8772 - accuracy: 0.7900 - precision: 0.4758 - recall: 0.6908 - auc: 0.8319 - prc: 0.5863 - val_loss: 0.4753 - val_tp: 219.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 98.0000 - val_accuracy: 0.7836 - val_precision: 0.5165 - val_recall: 0.6909 - val_auc: 0.8416 - val_prc: 0.6716
Epoch 117/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5136 - tp: 393.9298 - fp: 451.0000 - tn: 1871.1228 - fn: 182.1930 - accuracy: 0.7842 - precision: 0.4686 - recall: 0.6827 - auc: 0.8236 - prc: 0.5863 - val_loss: 0.4796 - val_tp: 222.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 95.0000 - val_accuracy: 0.7821 - val_precision: 0.5139 - val_recall: 0.7003 - val_auc: 0.8418 - val_prc: 0.6722
Epoch 118/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5085 - tp: 396.9298 - fp: 459.5439 - tn: 1871.1579 - fn: 170.6140 - accuracy: 0.7814 - precision: 0.4644 - recall: 0.6978 - auc: 0.8273 - prc: 0.5891 - val_loss: 0.4799 - val_tp: 224.0000 - val_fp: 209.0000 - val_tn: 874.0000 - val_fn: 93.0000 - val_accuracy: 0.7843 - val_precision: 0.5173 - val_recall: 0.7066 - val_auc: 0.8418 - val_prc: 0.6726
Epoch 119/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5050 - tp: 404.5088 - fp: 443.6316 - tn: 1876.5088 - fn: 173.5965 - accuracy: 0.7847 - precision: 0.4717 - recall: 0.6964 - auc: 0.8283 - prc: 0.5971 - val_loss: 0.4780 - val_tp: 222.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 95.0000 - val_accuracy: 0.7821 - val_precision: 0.5139 - val_recall: 0.7003 - val_auc: 0.8415 - val_prc: 0.6716
Epoch 120/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4942 - tp: 398.7018 - fp: 441.0877 - tn: 1886.1930 - fn: 172.2632 - accuracy: 0.7953 - precision: 0.4791 - recall: 0.6982 - auc: 0.8315 - prc: 0.6084 - val_loss: 0.4770 - val_tp: 221.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 96.0000 - val_accuracy: 0.7829 - val_precision: 0.5152 - val_recall: 0.6972 - val_auc: 0.8417 - val_prc: 0.6733
Epoch 121/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5142 - tp: 385.9649 - fp: 460.2982 - tn: 1875.3333 - fn: 176.6491 - accuracy: 0.7782 - precision: 0.4492 - recall: 0.6825 - auc: 0.8168 - prc: 0.5656 - val_loss: 0.4782 - val_tp: 225.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 92.0000 - val_accuracy: 0.7857 - val_precision: 0.5196 - val_recall: 0.7098 - val_auc: 0.8421 - val_prc: 0.6743
Epoch 122/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5042 - tp: 412.2982 - fp: 468.0175 - tn: 1844.9123 - fn: 173.0175 - accuracy: 0.7844 - precision: 0.4789 - recall: 0.7048 - auc: 0.8339 - prc: 0.6161 - val_loss: 0.4736 - val_tp: 220.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 97.0000 - val_accuracy: 0.7857 - val_precision: 0.5201 - val_recall: 0.6940 - val_auc: 0.8421 - val_prc: 0.6756
Epoch 123/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5119 - tp: 390.1754 - fp: 450.3509 - tn: 1868.7719 - fn: 188.9474 - accuracy: 0.7786 - precision: 0.4588 - recall: 0.6638 - auc: 0.8237 - prc: 0.6055 - val_loss: 0.4736 - val_tp: 219.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 98.0000 - val_accuracy: 0.7864 - val_precision: 0.5214 - val_recall: 0.6909 - val_auc: 0.8422 - val_prc: 0.6751
Epoch 124/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4951 - tp: 405.4386 - fp: 448.1754 - tn: 1879.3509 - fn: 165.2807 - accuracy: 0.7885 - precision: 0.4668 - recall: 0.7129 - auc: 0.8340 - prc: 0.5914 - val_loss: 0.4756 - val_tp: 220.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 97.0000 - val_accuracy: 0.7836 - val_precision: 0.5164 - val_recall: 0.6940 - val_auc: 0.8420 - val_prc: 0.6736
Epoch 125/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5025 - tp: 387.9298 - fp: 439.2105 - tn: 1894.2105 - fn: 176.8947 - accuracy: 0.7847 - precision: 0.4589 - recall: 0.6823 - auc: 0.8260 - prc: 0.5884 - val_loss: 0.4790 - val_tp: 227.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 90.0000 - val_accuracy: 0.7821 - val_precision: 0.5136 - val_recall: 0.7161 - val_auc: 0.8419 - val_prc: 0.6756
Epoch 126/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5172 - tp: 395.8070 - fp: 459.7719 - tn: 1862.6842 - fn: 179.9825 - accuracy: 0.7794 - precision: 0.4662 - recall: 0.6865 - auc: 0.8251 - prc: 0.5970 - val_loss: 0.4731 - val_tp: 222.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 95.0000 - val_accuracy: 0.7886 - val_precision: 0.5248 - val_recall: 0.7003 - val_auc: 0.8426 - val_prc: 0.6763
Epoch 127/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4887 - tp: 392.5263 - fp: 441.5789 - tn: 1896.8596 - fn: 167.2807 - accuracy: 0.7850 - precision: 0.4580 - recall: 0.7154 - auc: 0.8386 - prc: 0.6089 - val_loss: 0.4747 - val_tp: 222.0000 - val_fp: 207.0000 - val_tn: 876.0000 - val_fn: 95.0000 - val_accuracy: 0.7843 - val_precision: 0.5175 - val_recall: 0.7003 - val_auc: 0.8425 - val_prc: 0.6758
Epoch 128/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4921 - tp: 396.1930 - fp: 446.7719 - tn: 1887.0526 - fn: 168.2281 - accuracy: 0.7878 - precision: 0.4636 - recall: 0.7054 - auc: 0.8357 - prc: 0.5938 - val_loss: 0.4757 - val_tp: 226.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 91.0000 - val_accuracy: 0.7864 - val_precision: 0.5207 - val_recall: 0.7129 - val_auc: 0.8431 - val_prc: 0.6780
Epoch 129/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5117 - tp: 420.4035 - fp: 464.9298 - tn: 1850.9123 - fn: 162.0000 - accuracy: 0.7843 - precision: 0.4838 - recall: 0.7141 - auc: 0.8301 - prc: 0.6175 - val_loss: 0.4722 - val_tp: 221.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 96.0000 - val_accuracy: 0.7857 - val_precision: 0.5200 - val_recall: 0.6972 - val_auc: 0.8434 - val_prc: 0.6788
Epoch 130/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5117 - tp: 394.0877 - fp: 445.4035 - tn: 1874.4386 - fn: 184.3158 - accuracy: 0.7872 - precision: 0.4828 - recall: 0.6781 - auc: 0.8276 - prc: 0.6013 - val_loss: 0.4705 - val_tp: 220.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 97.0000 - val_accuracy: 0.7871 - val_precision: 0.5226 - val_recall: 0.6940 - val_auc: 0.8434 - val_prc: 0.6790
Epoch 131/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4954 - tp: 396.9123 - fp: 438.8246 - tn: 1883.0702 - fn: 179.4386 - accuracy: 0.7891 - precision: 0.4804 - recall: 0.6934 - auc: 0.8376 - prc: 0.6247 - val_loss: 0.4722 - val_tp: 220.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 97.0000 - val_accuracy: 0.7857 - val_precision: 0.5201 - val_recall: 0.6940 - val_auc: 0.8430 - val_prc: 0.6773
Epoch 132/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5073 - tp: 410.2982 - fp: 468.9825 - tn: 1849.7018 - fn: 169.2632 - accuracy: 0.7776 - precision: 0.4685 - recall: 0.7102 - auc: 0.8297 - prc: 0.6218 - val_loss: 0.4788 - val_tp: 223.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 94.0000 - val_accuracy: 0.7814 - val_precision: 0.5126 - val_recall: 0.7035 - val_auc: 0.8428 - val_prc: 0.6769
Epoch 133/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5028 - tp: 418.9474 - fp: 464.2105 - tn: 1856.0000 - fn: 159.0877 - accuracy: 0.7893 - precision: 0.4821 - recall: 0.7374 - auc: 0.8343 - prc: 0.5911 - val_loss: 0.4803 - val_tp: 222.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 95.0000 - val_accuracy: 0.7814 - val_precision: 0.5127 - val_recall: 0.7003 - val_auc: 0.8421 - val_prc: 0.6757
Epoch 134/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5078 - tp: 405.6667 - fp: 468.4386 - tn: 1846.0175 - fn: 178.1228 - accuracy: 0.7747 - precision: 0.4623 - recall: 0.6952 - auc: 0.8289 - prc: 0.6067 - val_loss: 0.4721 - val_tp: 221.0000 - val_fp: 198.0000 - val_tn: 885.0000 - val_fn: 96.0000 - val_accuracy: 0.7900 - val_precision: 0.5274 - val_recall: 0.6972 - val_auc: 0.8422 - val_prc: 0.6756
Epoch 135/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5034 - tp: 402.7895 - fp: 460.6316 - tn: 1864.6842 - fn: 170.1404 - accuracy: 0.7834 - precision: 0.4660 - recall: 0.6970 - auc: 0.8305 - prc: 0.5960 - val_loss: 0.4737 - val_tp: 221.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 96.0000 - val_accuracy: 0.7886 - val_precision: 0.5249 - val_recall: 0.6972 - val_auc: 0.8417 - val_prc: 0.6751
Epoch 136/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4793 - tp: 399.0351 - fp: 448.7018 - tn: 1887.9825 - fn: 162.5263 - accuracy: 0.7882 - precision: 0.4597 - recall: 0.7147 - auc: 0.8420 - prc: 0.6123 - val_loss: 0.4733 - val_tp: 222.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 95.0000 - val_accuracy: 0.7871 - val_precision: 0.5224 - val_recall: 0.7003 - val_auc: 0.8421 - val_prc: 0.6753
Epoch 137/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5151 - tp: 394.5789 - fp: 465.7544 - tn: 1865.8246 - fn: 172.0877 - accuracy: 0.7761 - precision: 0.4468 - recall: 0.6930 - auc: 0.8212 - prc: 0.5775 - val_loss: 0.4772 - val_tp: 225.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 92.0000 - val_accuracy: 0.7836 - val_precision: 0.5161 - val_recall: 0.7098 - val_auc: 0.8424 - val_prc: 0.6757
Epoch 138/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5230 - tp: 400.3333 - fp: 495.4912 - tn: 1833.1930 - fn: 169.2281 - accuracy: 0.7626 - precision: 0.4409 - recall: 0.6969 - auc: 0.8147 - prc: 0.5742 - val_loss: 0.4766 - val_tp: 224.0000 - val_fp: 209.0000 - val_tn: 874.0000 - val_fn: 93.0000 - val_accuracy: 0.7843 - val_precision: 0.5173 - val_recall: 0.7066 - val_auc: 0.8423 - val_prc: 0.6755
Epoch 139/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5133 - tp: 411.3860 - fp: 431.6842 - tn: 1884.6491 - fn: 170.5263 - accuracy: 0.7980 - precision: 0.5107 - recall: 0.7141 - auc: 0.8349 - prc: 0.6128 - val_loss: 0.4721 - val_tp: 220.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 97.0000 - val_accuracy: 0.7871 - val_precision: 0.5226 - val_recall: 0.6940 - val_auc: 0.8423 - val_prc: 0.6753
Epoch 140/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4990 - tp: 400.2807 - fp: 442.6491 - tn: 1878.5614 - fn: 176.7544 - accuracy: 0.7862 - precision: 0.4725 - recall: 0.6938 - auc: 0.8345 - prc: 0.6005 - val_loss: 0.4747 - val_tp: 222.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 95.0000 - val_accuracy: 0.7864 - val_precision: 0.5211 - val_recall: 0.7003 - val_auc: 0.8419 - val_prc: 0.6738
Epoch 141/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5057 - tp: 405.7895 - fp: 469.5439 - tn: 1856.9825 - fn: 165.9298 - accuracy: 0.7749 - precision: 0.4593 - recall: 0.7079 - auc: 0.8308 - prc: 0.6141 - val_loss: 0.4751 - val_tp: 225.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 92.0000 - val_accuracy: 0.7857 - val_precision: 0.5196 - val_recall: 0.7098 - val_auc: 0.8421 - val_prc: 0.6749
Epoch 142/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4874 - tp: 398.8246 - fp: 446.6140 - tn: 1888.5263 - fn: 164.2807 - accuracy: 0.7893 - precision: 0.4708 - recall: 0.7162 - auc: 0.8403 - prc: 0.6140 - val_loss: 0.4780 - val_tp: 226.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 91.0000 - val_accuracy: 0.7850 - val_precision: 0.5183 - val_recall: 0.7129 - val_auc: 0.8425 - val_prc: 0.6761
Epoch 143/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5016 - tp: 407.0351 - fp: 474.3158 - tn: 1853.4386 - fn: 163.4561 - accuracy: 0.7789 - precision: 0.4549 - recall: 0.7109 - auc: 0.8282 - prc: 0.5919 - val_loss: 0.4728 - val_tp: 221.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 96.0000 - val_accuracy: 0.7864 - val_precision: 0.5212 - val_recall: 0.6972 - val_auc: 0.8428 - val_prc: 0.6772
Epoch 144/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5036 - tp: 407.4912 - fp: 456.9298 - tn: 1872.4912 - fn: 161.3333 - accuracy: 0.7889 - precision: 0.4718 - recall: 0.7220 - auc: 0.8306 - prc: 0.6016 - val_loss: 0.4777 - val_tp: 225.0000 - val_fp: 207.0000 - val_tn: 876.0000 - val_fn: 92.0000 - val_accuracy: 0.7864 - val_precision: 0.5208 - val_recall: 0.7098 - val_auc: 0.8426 - val_prc: 0.6770
Epoch 145/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4978 - tp: 414.3333 - fp: 445.4912 - tn: 1865.1228 - fn: 173.2982 - accuracy: 0.7889 - precision: 0.4872 - recall: 0.7047 - auc: 0.8369 - prc: 0.6290 - val_loss: 0.4719 - val_tp: 222.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 95.0000 - val_accuracy: 0.7893 - val_precision: 0.5261 - val_recall: 0.7003 - val_auc: 0.8428 - val_prc: 0.6771
Epoch 146/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4978 - tp: 391.3158 - fp: 445.8246 - tn: 1881.6842 - fn: 179.4211 - accuracy: 0.7842 - precision: 0.4578 - recall: 0.6856 - auc: 0.8296 - prc: 0.5958 - val_loss: 0.4718 - val_tp: 220.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 97.0000 - val_accuracy: 0.7871 - val_precision: 0.5226 - val_recall: 0.6940 - val_auc: 0.8424 - val_prc: 0.6762
Epoch 147/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4951 - tp: 394.5088 - fp: 450.7719 - tn: 1882.2456 - fn: 170.7193 - accuracy: 0.7835 - precision: 0.4608 - recall: 0.6985 - auc: 0.8319 - prc: 0.6150 - val_loss: 0.4739 - val_tp: 224.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 93.0000 - val_accuracy: 0.7900 - val_precision: 0.5271 - val_recall: 0.7066 - val_auc: 0.8432 - val_prc: 0.6803
Epoch 148/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5007 - tp: 404.7193 - fp: 466.9298 - tn: 1862.5088 - fn: 164.0877 - accuracy: 0.7834 - precision: 0.4688 - recall: 0.7122 - auc: 0.8309 - prc: 0.6223 - val_loss: 0.4764 - val_tp: 227.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 90.0000 - val_accuracy: 0.7871 - val_precision: 0.5218 - val_recall: 0.7161 - val_auc: 0.8432 - val_prc: 0.6802
Epoch 149/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5122 - tp: 410.0702 - fp: 467.1053 - tn: 1854.7018 - fn: 166.3684 - accuracy: 0.7843 - precision: 0.4693 - recall: 0.7187 - auc: 0.8244 - prc: 0.5854 - val_loss: 0.4725 - val_tp: 222.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 95.0000 - val_accuracy: 0.7893 - val_precision: 0.5261 - val_recall: 0.7003 - val_auc: 0.8442 - val_prc: 0.6820
Epoch 150/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5081 - tp: 414.4386 - fp: 450.3333 - tn: 1862.5965 - fn: 170.8772 - accuracy: 0.7884 - precision: 0.4828 - recall: 0.7090 - auc: 0.8283 - prc: 0.6098 - val_loss: 0.4722 - val_tp: 223.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 94.0000 - val_accuracy: 0.7900 - val_precision: 0.5272 - val_recall: 0.7035 - val_auc: 0.8439 - val_prc: 0.6816
Epoch 151/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4905 - tp: 410.2105 - fp: 429.5439 - tn: 1896.6491 - fn: 161.8421 - accuracy: 0.8010 - precision: 0.5014 - recall: 0.7293 - auc: 0.8423 - prc: 0.6301 - val_loss: 0.4765 - val_tp: 225.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 92.0000 - val_accuracy: 0.7871 - val_precision: 0.5220 - val_recall: 0.7098 - val_auc: 0.8426 - val_prc: 0.6788
Epoch 152/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5121 - tp: 415.3684 - fp: 480.9298 - tn: 1837.5965 - fn: 164.3509 - accuracy: 0.7768 - precision: 0.4662 - recall: 0.7182 - auc: 0.8294 - prc: 0.6052 - val_loss: 0.4731 - val_tp: 223.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 94.0000 - val_accuracy: 0.7886 - val_precision: 0.5247 - val_recall: 0.7035 - val_auc: 0.8425 - val_prc: 0.6776
Epoch 153/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5128 - tp: 421.5263 - fp: 445.8246 - tn: 1857.6140 - fn: 173.2807 - accuracy: 0.7850 - precision: 0.4868 - recall: 0.7079 - auc: 0.8328 - prc: 0.6156 - val_loss: 0.4716 - val_tp: 223.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 94.0000 - val_accuracy: 0.7907 - val_precision: 0.5284 - val_recall: 0.7035 - val_auc: 0.8430 - val_prc: 0.6792
Epoch 154/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5002 - tp: 399.8596 - fp: 442.7544 - tn: 1878.0351 - fn: 177.5965 - accuracy: 0.7856 - precision: 0.4736 - recall: 0.6924 - auc: 0.8314 - prc: 0.6142 - val_loss: 0.4731 - val_tp: 222.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 95.0000 - val_accuracy: 0.7879 - val_precision: 0.5236 - val_recall: 0.7003 - val_auc: 0.8426 - val_prc: 0.6777
Epoch 155/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4978 - tp: 393.2807 - fp: 453.9825 - tn: 1876.0877 - fn: 174.8947 - accuracy: 0.7809 - precision: 0.4550 - recall: 0.6873 - auc: 0.8321 - prc: 0.5904 - val_loss: 0.4701 - val_tp: 220.0000 - val_fp: 193.0000 - val_tn: 890.0000 - val_fn: 97.0000 - val_accuracy: 0.7929 - val_precision: 0.5327 - val_recall: 0.6940 - val_auc: 0.8429 - val_prc: 0.6773
Epoch 156/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5159 - tp: 381.2105 - fp: 471.2982 - tn: 1858.8421 - fn: 186.8947 - accuracy: 0.7704 - precision: 0.4388 - recall: 0.6575 - auc: 0.8163 - prc: 0.5778 - val_loss: 0.4703 - val_tp: 220.0000 - val_fp: 196.0000 - val_tn: 887.0000 - val_fn: 97.0000 - val_accuracy: 0.7907 - val_precision: 0.5288 - val_recall: 0.6940 - val_auc: 0.8433 - val_prc: 0.6774
Epoch 157/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4888 - tp: 383.7368 - fp: 440.6491 - tn: 1900.8421 - fn: 173.0175 - accuracy: 0.7894 - precision: 0.4598 - recall: 0.6963 - auc: 0.8351 - prc: 0.6020 - val_loss: 0.4741 - val_tp: 224.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 93.0000 - val_accuracy: 0.7900 - val_precision: 0.5271 - val_recall: 0.7066 - val_auc: 0.8435 - val_prc: 0.6793
Epoch 158/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5470 - tp: 397.4912 - fp: 466.5263 - tn: 1856.9474 - fn: 177.2807 - accuracy: 0.7728 - precision: 0.4437 - recall: 0.6667 - auc: 0.7970 - prc: 0.5383 - val_loss: 0.4803 - val_tp: 229.0000 - val_fp: 207.0000 - val_tn: 876.0000 - val_fn: 88.0000 - val_accuracy: 0.7893 - val_precision: 0.5252 - val_recall: 0.7224 - val_auc: 0.8435 - val_prc: 0.6799
Epoch 159/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5029 - tp: 388.8070 - fp: 477.5088 - tn: 1859.7193 - fn: 172.2105 - accuracy: 0.7710 - precision: 0.4411 - recall: 0.7005 - auc: 0.8270 - prc: 0.5940 - val_loss: 0.4747 - val_tp: 226.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 91.0000 - val_accuracy: 0.7900 - val_precision: 0.5268 - val_recall: 0.7129 - val_auc: 0.8437 - val_prc: 0.6799
Epoch 160/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5236 - tp: 395.8947 - fp: 472.9298 - tn: 1845.7719 - fn: 183.6491 - accuracy: 0.7705 - precision: 0.4533 - recall: 0.6706 - auc: 0.8168 - prc: 0.5896 - val_loss: 0.4801 - val_tp: 230.0000 - val_fp: 209.0000 - val_tn: 874.0000 - val_fn: 87.0000 - val_accuracy: 0.7886 - val_precision: 0.5239 - val_recall: 0.7256 - val_auc: 0.8437 - val_prc: 0.6798
Epoch 161/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4918 - tp: 399.1754 - fp: 451.9298 - tn: 1874.1930 - fn: 172.9474 - accuracy: 0.7898 - precision: 0.4704 - recall: 0.7153 - auc: 0.8399 - prc: 0.6024 - val_loss: 0.4772 - val_tp: 227.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 90.0000 - val_accuracy: 0.7914 - val_precision: 0.5291 - val_recall: 0.7161 - val_auc: 0.8435 - val_prc: 0.6790
Epoch 162/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5203 - tp: 404.4912 - fp: 459.9825 - tn: 1859.5789 - fn: 174.1930 - accuracy: 0.7756 - precision: 0.4660 - recall: 0.6953 - auc: 0.8229 - prc: 0.6004 - val_loss: 0.4709 - val_tp: 221.0000 - val_fp: 190.0000 - val_tn: 893.0000 - val_fn: 96.0000 - val_accuracy: 0.7957 - val_precision: 0.5377 - val_recall: 0.6972 - val_auc: 0.8439 - val_prc: 0.6805
Epoch 163/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4976 - tp: 413.7018 - fp: 440.6667 - tn: 1876.7544 - fn: 167.1228 - accuracy: 0.7904 - precision: 0.4874 - recall: 0.7158 - auc: 0.8391 - prc: 0.6320 - val_loss: 0.4766 - val_tp: 225.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 92.0000 - val_accuracy: 0.7879 - val_precision: 0.5233 - val_recall: 0.7098 - val_auc: 0.8433 - val_prc: 0.6797
Epoch 164/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5124 - tp: 419.6140 - fp: 477.3684 - tn: 1833.0526 - fn: 168.2105 - accuracy: 0.7769 - precision: 0.4756 - recall: 0.7167 - auc: 0.8345 - prc: 0.6157 - val_loss: 0.4705 - val_tp: 220.0000 - val_fp: 193.0000 - val_tn: 890.0000 - val_fn: 97.0000 - val_accuracy: 0.7929 - val_precision: 0.5327 - val_recall: 0.6940 - val_auc: 0.8436 - val_prc: 0.6801
Epoch 165/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5049 - tp: 406.0175 - fp: 447.0175 - tn: 1870.9649 - fn: 174.2456 - accuracy: 0.7836 - precision: 0.4746 - recall: 0.6981 - auc: 0.8305 - prc: 0.6169 - val_loss: 0.4696 - val_tp: 220.0000 - val_fp: 194.0000 - val_tn: 889.0000 - val_fn: 97.0000 - val_accuracy: 0.7921 - val_precision: 0.5314 - val_recall: 0.6940 - val_auc: 0.8437 - val_prc: 0.6801
Epoch 166/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4781 - tp: 400.0351 - fp: 445.4386 - tn: 1887.0526 - fn: 165.7193 - accuracy: 0.7924 - precision: 0.4773 - recall: 0.7215 - auc: 0.8483 - prc: 0.6237 - val_loss: 0.4688 - val_tp: 219.0000 - val_fp: 194.0000 - val_tn: 889.0000 - val_fn: 98.0000 - val_accuracy: 0.7914 - val_precision: 0.5303 - val_recall: 0.6909 - val_auc: 0.8436 - val_prc: 0.6804
Epoch 167/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5143 - tp: 388.3333 - fp: 449.3158 - tn: 1873.7368 - fn: 186.8596 - accuracy: 0.7819 - precision: 0.4675 - recall: 0.6688 - auc: 0.8252 - prc: 0.5890 - val_loss: 0.4715 - val_tp: 223.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 94.0000 - val_accuracy: 0.7907 - val_precision: 0.5284 - val_recall: 0.7035 - val_auc: 0.8437 - val_prc: 0.6811
Epoch 168/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4926 - tp: 404.8421 - fp: 434.0000 - tn: 1898.7719 - fn: 160.6316 - accuracy: 0.7975 - precision: 0.4891 - recall: 0.7224 - auc: 0.8396 - prc: 0.6224 - val_loss: 0.4695 - val_tp: 221.0000 - val_fp: 194.0000 - val_tn: 889.0000 - val_fn: 96.0000 - val_accuracy: 0.7929 - val_precision: 0.5325 - val_recall: 0.6972 - val_auc: 0.8441 - val_prc: 0.6804
Epoch 169/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5063 - tp: 404.0000 - fp: 444.8070 - tn: 1879.1228 - fn: 170.3158 - accuracy: 0.7871 - precision: 0.4810 - recall: 0.6990 - auc: 0.8334 - prc: 0.5970 - val_loss: 0.4687 - val_tp: 221.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 96.0000 - val_accuracy: 0.7907 - val_precision: 0.5287 - val_recall: 0.6972 - val_auc: 0.8442 - val_prc: 0.6812
Epoch 170/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4892 - tp: 409.7368 - fp: 432.8772 - tn: 1895.7018 - fn: 159.9298 - accuracy: 0.7978 - precision: 0.4899 - recall: 0.7240 - auc: 0.8419 - prc: 0.6172 - val_loss: 0.4687 - val_tp: 221.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 96.0000 - val_accuracy: 0.7886 - val_precision: 0.5249 - val_recall: 0.6972 - val_auc: 0.8438 - val_prc: 0.6800
Epoch 171/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5125 - tp: 405.5789 - fp: 454.2456 - tn: 1871.2982 - fn: 167.1228 - accuracy: 0.7843 - precision: 0.4690 - recall: 0.7067 - auc: 0.8259 - prc: 0.5876 - val_loss: 0.4746 - val_tp: 224.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 93.0000 - val_accuracy: 0.7864 - val_precision: 0.5209 - val_recall: 0.7066 - val_auc: 0.8436 - val_prc: 0.6816
Epoch 172/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5034 - tp: 404.2982 - fp: 463.9649 - tn: 1858.7719 - fn: 171.2105 - accuracy: 0.7788 - precision: 0.4680 - recall: 0.7065 - auc: 0.8317 - prc: 0.6240 - val_loss: 0.4722 - val_tp: 224.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 93.0000 - val_accuracy: 0.7914 - val_precision: 0.5296 - val_recall: 0.7066 - val_auc: 0.8439 - val_prc: 0.6822
Epoch 173/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5128 - tp: 412.7544 - fp: 461.5439 - tn: 1851.1930 - fn: 172.7544 - accuracy: 0.7791 - precision: 0.4722 - recall: 0.7047 - auc: 0.8279 - prc: 0.6140 - val_loss: 0.4705 - val_tp: 222.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 95.0000 - val_accuracy: 0.7900 - val_precision: 0.5273 - val_recall: 0.7003 - val_auc: 0.8442 - val_prc: 0.6817
Epoch 174/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5058 - tp: 406.0175 - fp: 433.4912 - tn: 1884.9825 - fn: 173.7544 - accuracy: 0.7957 - precision: 0.4920 - recall: 0.6997 - auc: 0.8324 - prc: 0.6034 - val_loss: 0.4721 - val_tp: 222.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 95.0000 - val_accuracy: 0.7879 - val_precision: 0.5236 - val_recall: 0.7003 - val_auc: 0.8440 - val_prc: 0.6809
Epoch 175/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4948 - tp: 402.7895 - fp: 451.3684 - tn: 1878.3509 - fn: 165.7368 - accuracy: 0.7894 - precision: 0.4767 - recall: 0.7149 - auc: 0.8396 - prc: 0.6049 - val_loss: 0.4737 - val_tp: 225.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 92.0000 - val_accuracy: 0.7900 - val_precision: 0.5269 - val_recall: 0.7098 - val_auc: 0.8441 - val_prc: 0.6818
Epoch 176/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4913 - tp: 395.8421 - fp: 456.3860 - tn: 1872.8421 - fn: 173.1754 - accuracy: 0.7881 - precision: 0.4723 - recall: 0.7094 - auc: 0.8396 - prc: 0.6228 - val_loss: 0.4759 - val_tp: 226.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 91.0000 - val_accuracy: 0.7879 - val_precision: 0.5231 - val_recall: 0.7129 - val_auc: 0.8437 - val_prc: 0.6813
Epoch 177/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5027 - tp: 397.2281 - fp: 446.9825 - tn: 1877.4737 - fn: 176.5614 - accuracy: 0.7851 - precision: 0.4680 - recall: 0.6908 - auc: 0.8298 - prc: 0.6099 - val_loss: 0.4796 - val_tp: 229.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 88.0000 - val_accuracy: 0.7857 - val_precision: 0.5193 - val_recall: 0.7224 - val_auc: 0.8437 - val_prc: 0.6810
Epoch 178/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5098 - tp: 410.2807 - fp: 466.1579 - tn: 1848.0175 - fn: 173.7895 - accuracy: 0.7784 - precision: 0.4707 - recall: 0.7113 - auc: 0.8298 - prc: 0.6158 - val_loss: 0.4753 - val_tp: 223.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 94.0000 - val_accuracy: 0.7871 - val_precision: 0.5222 - val_recall: 0.7035 - val_auc: 0.8432 - val_prc: 0.6799
Epoch 179/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5003 - tp: 417.6842 - fp: 451.0877 - tn: 1851.2807 - fn: 178.1930 - accuracy: 0.7887 - precision: 0.4942 - recall: 0.7058 - auc: 0.8418 - prc: 0.6338 - val_loss: 0.4712 - val_tp: 222.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 95.0000 - val_accuracy: 0.7914 - val_precision: 0.5298 - val_recall: 0.7003 - val_auc: 0.8438 - val_prc: 0.6813
Epoch 180/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5229 - tp: 407.0877 - fp: 433.6491 - tn: 1877.0351 - fn: 180.4737 - accuracy: 0.7851 - precision: 0.4869 - recall: 0.6832 - auc: 0.8226 - prc: 0.6126 - val_loss: 0.4683 - val_tp: 221.0000 - val_fp: 192.0000 - val_tn: 891.0000 - val_fn: 96.0000 - val_accuracy: 0.7943 - val_precision: 0.5351 - val_recall: 0.6972 - val_auc: 0.8438 - val_prc: 0.6817
Epoch 181/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5008 - tp: 404.4737 - fp: 423.9298 - tn: 1892.1053 - fn: 177.7368 - accuracy: 0.7964 - precision: 0.4973 - recall: 0.6923 - auc: 0.8359 - prc: 0.6307 - val_loss: 0.4698 - val_tp: 222.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 95.0000 - val_accuracy: 0.7879 - val_precision: 0.5236 - val_recall: 0.7003 - val_auc: 0.8429 - val_prc: 0.6807
Epoch 182/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4842 - tp: 385.2982 - fp: 424.4737 - tn: 1918.2456 - fn: 170.2281 - accuracy: 0.7963 - precision: 0.4709 - recall: 0.6910 - auc: 0.8384 - prc: 0.5948 - val_loss: 0.4688 - val_tp: 221.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 96.0000 - val_accuracy: 0.7886 - val_precision: 0.5249 - val_recall: 0.6972 - val_auc: 0.8438 - val_prc: 0.6821
Epoch 183/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4904 - tp: 390.8596 - fp: 448.5965 - tn: 1890.8596 - fn: 167.9298 - accuracy: 0.7883 - precision: 0.4588 - recall: 0.6979 - auc: 0.8347 - prc: 0.5864 - val_loss: 0.4781 - val_tp: 229.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 88.0000 - val_accuracy: 0.7814 - val_precision: 0.5123 - val_recall: 0.7224 - val_auc: 0.8441 - val_prc: 0.6830
Epoch 184/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5093 - tp: 424.1228 - fp: 463.5088 - tn: 1853.2982 - fn: 157.3158 - accuracy: 0.7844 - precision: 0.4762 - recall: 0.7288 - auc: 0.8294 - prc: 0.6049 - val_loss: 0.4719 - val_tp: 222.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 95.0000 - val_accuracy: 0.7900 - val_precision: 0.5273 - val_recall: 0.7003 - val_auc: 0.8444 - val_prc: 0.6835
Epoch 185/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5003 - tp: 410.5614 - fp: 460.4912 - tn: 1854.6140 - fn: 172.5789 - accuracy: 0.7823 - precision: 0.4665 - recall: 0.6954 - auc: 0.8343 - prc: 0.6097 - val_loss: 0.4675 - val_tp: 220.0000 - val_fp: 189.0000 - val_tn: 894.0000 - val_fn: 97.0000 - val_accuracy: 0.7957 - val_precision: 0.5379 - val_recall: 0.6940 - val_auc: 0.8447 - val_prc: 0.6839
Epoch 186/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5041 - tp: 398.0000 - fp: 436.9123 - tn: 1898.4211 - fn: 164.9123 - accuracy: 0.7936 - precision: 0.4761 - recall: 0.7146 - auc: 0.8286 - prc: 0.5891 - val_loss: 0.4679 - val_tp: 220.0000 - val_fp: 188.0000 - val_tn: 895.0000 - val_fn: 97.0000 - val_accuracy: 0.7964 - val_precision: 0.5392 - val_recall: 0.6940 - val_auc: 0.8449 - val_prc: 0.6842
Epoch 187/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5063 - tp: 396.0877 - fp: 441.7719 - tn: 1884.0526 - fn: 176.3333 - accuracy: 0.7853 - precision: 0.4652 - recall: 0.6830 - auc: 0.8257 - prc: 0.5908 - val_loss: 0.4701 - val_tp: 223.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 94.0000 - val_accuracy: 0.7921 - val_precision: 0.5310 - val_recall: 0.7035 - val_auc: 0.8446 - val_prc: 0.6841
Epoch 188/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5136 - tp: 417.4737 - fp: 471.1754 - tn: 1836.2281 - fn: 173.3684 - accuracy: 0.7793 - precision: 0.4771 - recall: 0.7226 - auc: 0.8324 - prc: 0.6067 - val_loss: 0.4687 - val_tp: 220.0000 - val_fp: 192.0000 - val_tn: 891.0000 - val_fn: 97.0000 - val_accuracy: 0.7936 - val_precision: 0.5340 - val_recall: 0.6940 - val_auc: 0.8449 - val_prc: 0.6838
Epoch 189/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5091 - tp: 401.9298 - fp: 459.5088 - tn: 1859.1228 - fn: 177.6842 - accuracy: 0.7777 - precision: 0.4595 - recall: 0.6914 - auc: 0.8234 - prc: 0.6039 - val_loss: 0.4678 - val_tp: 224.0000 - val_fp: 190.0000 - val_tn: 893.0000 - val_fn: 93.0000 - val_accuracy: 0.7979 - val_precision: 0.5411 - val_recall: 0.7066 - val_auc: 0.8457 - val_prc: 0.6846
Epoch 190/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5001 - tp: 393.5088 - fp: 419.5614 - tn: 1913.7368 - fn: 171.4386 - accuracy: 0.7960 - precision: 0.4750 - recall: 0.6821 - auc: 0.8289 - prc: 0.5971 - val_loss: 0.4665 - val_tp: 222.0000 - val_fp: 190.0000 - val_tn: 893.0000 - val_fn: 95.0000 - val_accuracy: 0.7964 - val_precision: 0.5388 - val_recall: 0.7003 - val_auc: 0.8460 - val_prc: 0.6862
Epoch 191/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5022 - tp: 405.1404 - fp: 443.1579 - tn: 1884.8070 - fn: 165.1404 - accuracy: 0.7908 - precision: 0.4823 - recall: 0.7141 - auc: 0.8361 - prc: 0.6121 - val_loss: 0.4681 - val_tp: 221.0000 - val_fp: 192.0000 - val_tn: 891.0000 - val_fn: 96.0000 - val_accuracy: 0.7943 - val_precision: 0.5351 - val_recall: 0.6972 - val_auc: 0.8452 - val_prc: 0.6855
Epoch 192/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5020 - tp: 407.3860 - fp: 443.3860 - tn: 1880.9123 - fn: 166.5614 - accuracy: 0.7887 - precision: 0.4859 - recall: 0.7087 - auc: 0.8349 - prc: 0.6215 - val_loss: 0.4720 - val_tp: 224.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 93.0000 - val_accuracy: 0.7907 - val_precision: 0.5283 - val_recall: 0.7066 - val_auc: 0.8443 - val_prc: 0.6831
Epoch 193/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5013 - tp: 413.9298 - fp: 445.3158 - tn: 1875.2456 - fn: 163.7544 - accuracy: 0.7936 - precision: 0.4875 - recall: 0.7216 - auc: 0.8332 - prc: 0.6306 - val_loss: 0.4711 - val_tp: 221.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 96.0000 - val_accuracy: 0.7886 - val_precision: 0.5249 - val_recall: 0.6972 - val_auc: 0.8443 - val_prc: 0.6825
Epoch 194/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5144 - tp: 402.8421 - fp: 448.8421 - tn: 1866.9649 - fn: 179.5965 - accuracy: 0.7774 - precision: 0.4661 - recall: 0.6814 - auc: 0.8203 - prc: 0.6123 - val_loss: 0.4691 - val_tp: 219.0000 - val_fp: 196.0000 - val_tn: 887.0000 - val_fn: 98.0000 - val_accuracy: 0.7900 - val_precision: 0.5277 - val_recall: 0.6909 - val_auc: 0.8443 - val_prc: 0.6824
Epoch 195/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5133 - tp: 402.1404 - fp: 455.1404 - tn: 1866.1930 - fn: 174.7719 - accuracy: 0.7761 - precision: 0.4554 - recall: 0.6844 - auc: 0.8234 - prc: 0.5833 - val_loss: 0.4719 - val_tp: 220.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 97.0000 - val_accuracy: 0.7900 - val_precision: 0.5276 - val_recall: 0.6940 - val_auc: 0.8441 - val_prc: 0.6818
Epoch 196/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5260 - tp: 381.9649 - fp: 440.2632 - tn: 1884.5614 - fn: 191.4561 - accuracy: 0.7802 - precision: 0.4623 - recall: 0.6612 - auc: 0.8115 - prc: 0.5812 - val_loss: 0.4729 - val_tp: 220.0000 - val_fp: 195.0000 - val_tn: 888.0000 - val_fn: 97.0000 - val_accuracy: 0.7914 - val_precision: 0.5301 - val_recall: 0.6940 - val_auc: 0.8438 - val_prc: 0.6811
Epoch 197/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4924 - tp: 406.1053 - fp: 453.0526 - tn: 1874.5263 - fn: 164.5614 - accuracy: 0.7891 - precision: 0.4773 - recall: 0.7262 - auc: 0.8439 - prc: 0.5997 - val_loss: 0.4692 - val_tp: 218.0000 - val_fp: 190.0000 - val_tn: 893.0000 - val_fn: 99.0000 - val_accuracy: 0.7936 - val_precision: 0.5343 - val_recall: 0.6877 - val_auc: 0.8449 - val_prc: 0.6832
Epoch 198/200
56/56 [==============================] - 0s 1ms/step - loss: 0.4981 - tp: 397.2807 - fp: 425.5965 - tn: 1898.1228 - fn: 177.2456 - accuracy: 0.7920 - precision: 0.4876 - recall: 0.6903 - auc: 0.8381 - prc: 0.6076 - val_loss: 0.4688 - val_tp: 221.0000 - val_fp: 189.0000 - val_tn: 894.0000 - val_fn: 96.0000 - val_accuracy: 0.7964 - val_precision: 0.5390 - val_recall: 0.6972 - val_auc: 0.8452 - val_prc: 0.6844
Epoch 199/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5092 - tp: 400.3333 - fp: 468.9825 - tn: 1859.0702 - fn: 169.8596 - accuracy: 0.7759 - precision: 0.4578 - recall: 0.6933 - auc: 0.8300 - prc: 0.5927 - val_loss: 0.4696 - val_tp: 222.0000 - val_fp: 192.0000 - val_tn: 891.0000 - val_fn: 95.0000 - val_accuracy: 0.7950 - val_precision: 0.5362 - val_recall: 0.7003 - val_auc: 0.8457 - val_prc: 0.6849
Epoch 200/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5239 - tp: 400.6667 - fp: 452.4737 - tn: 1862.4737 - fn: 182.6316 - accuracy: 0.7779 - precision: 0.4630 - recall: 0.6696 - auc: 0.8157 - prc: 0.5753 - val_loss: 0.4709 - val_tp: 220.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 97.0000 - val_accuracy: 0.7900 - val_precision: 0.5276 - val_recall: 0.6940 - val_auc: 0.8452 - val_prc: 0.6851


model2.summary()

Model: "sequential_15"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_39 (Dense)             (None, 16)                192       
_________________________________________________________________
dropout_22 (Dropout)         (None, 16)                0         
_________________________________________________________________
dense_40 (Dense)             (None, 1)                 17        
=================================================================
Total params: 209
Trainable params: 209
Non-trainable params: 0
_________________________________________________________________


history_df = pd.DataFrame(history2.history)
history_df['epoch']=history2.epoch
display(history_df)
train_acc = history_df.loc[199,'accuracy']
train_recall = history_df.loc[199,'recall']
train_loss = history_df.loc[199,'loss']


results_df = results_df['model1']

results2=model2.evaluate(X_test, y_test.values)

temp_df = pd.DataFrame(results2, index=model2.metrics_names, columns=['model2'])

results_df = pd.merge(results_df, temp_df, left_index=True, right_index=True)

results_df

94/94 [==============================] - 1s 1ms/step - loss: 0.4711 - tp: 442.0000 - fp: 451.0000 - tn: 1938.0000 - fn: 169.0000 - accuracy: 0.7933 - precision: 0.4950 - recall: 0.7234 - auc: 0.8493 - prc: 0.6710


plt.figure(figsize=(10,10))
plot_metrics(history2)


y_predict = (model2.predict(X_test) > THRESHOLD).astype('int32')
make_confusion_matrix(model2,y_test, y_predict, cmap='coolwarm')


print(f'Model test loss is: {results_df.loc["loss","model2"]:0.4f}, train loss is {train_loss:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model2"]:0.4f}, train accuracy is {train_acc:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model2"]:0.4f}, train recall is {train_recall:0.4f}')

Model test loss is: 0.4711, train loss is 0.5035
Model test accuracy is: 0.7933, train accuracy is 0.7841
Model test recall is: 0.7234, train recall is 0.7069


%%time
model3 = make_model(dropout=True, learning_rate=0.001, activation='tanh')

history3 = model3.fit(X_train, y_train, epochs=EPOCHS+100, batch_size=BATCH_SIZE, use_multiprocessing=True, validation_split=0.2, class_weight=class_weight, verbose=0)

CPU times: user 25.7 s, sys: 4.11 s, total: 29.8 s
Wall time: 15.1 s


results_df = results_df.loc[:,['model1','model2']]

results3=model3.evaluate(X_test, y_test.values)

temp_df = pd.DataFrame(results3, index=model3.metrics_names, columns=['model2-tanh'])

results_df = pd.merge(results_df, temp_df, left_index=True, right_index=True)

results_df

94/94 [==============================] - 1s 1ms/step - loss: 0.5014 - tp: 444.0000 - fp: 529.0000 - tn: 1860.0000 - fn: 167.0000 - accuracy: 0.7680 - precision: 0.4563 - recall: 0.7267 - auc: 0.8272 - prc: 0.5875


print(f'Model test loss is: {results_df.loc["loss","model2-tanh"]:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model2-tanh"]:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model2-tanh"]:0.4f}')

Model test loss is: 0.5014
Model test accuracy is: 0.7680
Model test recall is: 0.7267


%%time
model4 = make_model2(dropout=True, learning_rate=0.002)

history4 = model4.fit(X_train, y_train, epochs=EPOCHS+100, batch_size=2000, use_multiprocessing=True, validation_split=0.2, class_weight=class_weight, verbose=1)

Epoch 1/200
3/3 [==============================] - 3s 368ms/step - loss: 0.7792 - tp: 1112.2500 - fp: 3250.5000 - tn: 2595.7500 - fn: 341.5000 - accuracy: 0.5180 - precision: 0.2608 - recall: 0.7633 - auc: 0.6751 - prc: 0.4009 - val_loss: 0.8621 - val_tp: 310.0000 - val_fp: 1074.0000 - val_tn: 9.0000 - val_fn: 7.0000 - val_accuracy: 0.2279 - val_precision: 0.2240 - val_recall: 0.9779 - val_auc: 0.5174 - val_prc: 0.2292
Epoch 2/200
3/3 [==============================] - 0s 13ms/step - loss: 0.7541 - tp: 670.2500 - fp: 2681.0000 - tn: 773.2500 - fn: 175.5000 - accuracy: 0.3321 - precision: 0.1989 - recall: 0.7967 - auc: 0.5051 - prc: 0.1933 - val_loss: 0.8155 - val_tp: 307.0000 - val_fp: 1020.0000 - val_tn: 63.0000 - val_fn: 10.0000 - val_accuracy: 0.2643 - val_precision: 0.2313 - val_recall: 0.9685 - val_auc: 0.5716 - val_prc: 0.2583
Epoch 3/200
3/3 [==============================] - 0s 16ms/step - loss: 0.7456 - tp: 631.2500 - fp: 2499.7500 - tn: 940.2500 - fn: 228.7500 - accuracy: 0.3642 - precision: 0.2023 - recall: 0.7339 - auc: 0.5094 - prc: 0.2071 - val_loss: 0.7839 - val_tp: 300.0000 - val_fp: 943.0000 - val_tn: 140.0000 - val_fn: 17.0000 - val_accuracy: 0.3143 - val_precision: 0.2414 - val_recall: 0.9464 - val_auc: 0.6130 - val_prc: 0.2877
Epoch 4/200
3/3 [==============================] - 0s 17ms/step - loss: 0.7133 - tp: 652.7500 - fp: 2426.7500 - tn: 1020.2500 - fn: 200.2500 - accuracy: 0.3889 - precision: 0.2121 - recall: 0.7662 - auc: 0.5577 - prc: 0.2335 - val_loss: 0.7584 - val_tp: 295.0000 - val_fp: 849.0000 - val_tn: 234.0000 - val_fn: 22.0000 - val_accuracy: 0.3779 - val_precision: 0.2579 - val_recall: 0.9306 - val_auc: 0.6425 - val_prc: 0.3136
Epoch 5/200
3/3 [==============================] - 0s 16ms/step - loss: 0.7035 - tp: 640.0000 - fp: 2299.0000 - tn: 1147.2500 - fn: 213.7500 - accuracy: 0.4155 - precision: 0.2183 - recall: 0.7541 - auc: 0.5612 - prc: 0.2296 - val_loss: 0.7376 - val_tp: 290.0000 - val_fp: 785.0000 - val_tn: 298.0000 - val_fn: 27.0000 - val_accuracy: 0.4200 - val_precision: 0.2698 - val_recall: 0.9148 - val_auc: 0.6655 - val_prc: 0.3378
Epoch 6/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6950 - tp: 634.7500 - fp: 2209.0000 - tn: 1242.7500 - fn: 213.5000 - accuracy: 0.4350 - precision: 0.2224 - recall: 0.7497 - auc: 0.5832 - prc: 0.2405 - val_loss: 0.7206 - val_tp: 286.0000 - val_fp: 737.0000 - val_tn: 346.0000 - val_fn: 31.0000 - val_accuracy: 0.4514 - val_precision: 0.2796 - val_recall: 0.9022 - val_auc: 0.6824 - val_prc: 0.3549
Epoch 7/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6974 - tp: 631.2500 - fp: 2121.5000 - tn: 1325.2500 - fn: 222.0000 - accuracy: 0.4534 - precision: 0.2291 - recall: 0.7387 - auc: 0.5865 - prc: 0.2470 - val_loss: 0.7089 - val_tp: 283.0000 - val_fp: 687.0000 - val_tn: 396.0000 - val_fn: 34.0000 - val_accuracy: 0.4850 - val_precision: 0.2918 - val_recall: 0.8927 - val_auc: 0.6961 - val_prc: 0.3738
Epoch 8/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6780 - tp: 650.7500 - fp: 2084.5000 - tn: 1360.2500 - fn: 204.5000 - accuracy: 0.4668 - precision: 0.2388 - recall: 0.7636 - auc: 0.6112 - prc: 0.2633 - val_loss: 0.6975 - val_tp: 278.0000 - val_fp: 654.0000 - val_tn: 429.0000 - val_fn: 39.0000 - val_accuracy: 0.5050 - val_precision: 0.2983 - val_recall: 0.8770 - val_auc: 0.7056 - val_prc: 0.3844
Epoch 9/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6647 - tp: 645.7500 - fp: 1994.0000 - tn: 1454.7500 - fn: 205.5000 - accuracy: 0.4868 - precision: 0.2440 - recall: 0.7583 - auc: 0.6338 - prc: 0.2863 - val_loss: 0.6864 - val_tp: 276.0000 - val_fp: 618.0000 - val_tn: 465.0000 - val_fn: 41.0000 - val_accuracy: 0.5293 - val_precision: 0.3087 - val_recall: 0.8707 - val_auc: 0.7141 - val_prc: 0.3984
Epoch 10/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6647 - tp: 645.7500 - fp: 1921.5000 - tn: 1527.7500 - fn: 205.0000 - accuracy: 0.5045 - precision: 0.2508 - recall: 0.7594 - auc: 0.6468 - prc: 0.2965 - val_loss: 0.6776 - val_tp: 275.0000 - val_fp: 595.0000 - val_tn: 488.0000 - val_fn: 42.0000 - val_accuracy: 0.5450 - val_precision: 0.3161 - val_recall: 0.8675 - val_auc: 0.7204 - val_prc: 0.4084
Epoch 11/200
3/3 [==============================] - 0s 15ms/step - loss: 0.6554 - tp: 639.0000 - fp: 1892.5000 - tn: 1557.7500 - fn: 210.7500 - accuracy: 0.5119 - precision: 0.2540 - recall: 0.7543 - auc: 0.6519 - prc: 0.2998 - val_loss: 0.6697 - val_tp: 274.0000 - val_fp: 577.0000 - val_tn: 506.0000 - val_fn: 43.0000 - val_accuracy: 0.5571 - val_precision: 0.3220 - val_recall: 0.8644 - val_auc: 0.7258 - val_prc: 0.4175
Epoch 12/200
3/3 [==============================] - 0s 15ms/step - loss: 0.6515 - tp: 639.5000 - fp: 1852.2500 - tn: 1604.2500 - fn: 204.0000 - accuracy: 0.5211 - precision: 0.2548 - recall: 0.7594 - auc: 0.6636 - prc: 0.3103 - val_loss: 0.6627 - val_tp: 270.0000 - val_fp: 567.0000 - val_tn: 516.0000 - val_fn: 47.0000 - val_accuracy: 0.5614 - val_precision: 0.3226 - val_recall: 0.8517 - val_auc: 0.7295 - val_prc: 0.4222
Epoch 13/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6518 - tp: 647.5000 - fp: 1809.5000 - tn: 1637.0000 - fn: 206.0000 - accuracy: 0.5314 - precision: 0.2642 - recall: 0.7605 - auc: 0.6673 - prc: 0.3169 - val_loss: 0.6585 - val_tp: 270.0000 - val_fp: 560.0000 - val_tn: 523.0000 - val_fn: 47.0000 - val_accuracy: 0.5664 - val_precision: 0.3253 - val_recall: 0.8517 - val_auc: 0.7332 - val_prc: 0.4288
Epoch 14/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6442 - tp: 660.0000 - fp: 1769.5000 - tn: 1682.0000 - fn: 188.5000 - accuracy: 0.5456 - precision: 0.2723 - recall: 0.7783 - auc: 0.6867 - prc: 0.3253 - val_loss: 0.6545 - val_tp: 268.0000 - val_fp: 554.0000 - val_tn: 529.0000 - val_fn: 49.0000 - val_accuracy: 0.5693 - val_precision: 0.3260 - val_recall: 0.8454 - val_auc: 0.7364 - val_prc: 0.4339
Epoch 15/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6406 - tp: 652.5000 - fp: 1780.0000 - tn: 1667.5000 - fn: 200.0000 - accuracy: 0.5370 - precision: 0.2661 - recall: 0.7645 - auc: 0.6897 - prc: 0.3364 - val_loss: 0.6506 - val_tp: 268.0000 - val_fp: 542.0000 - val_tn: 541.0000 - val_fn: 49.0000 - val_accuracy: 0.5779 - val_precision: 0.3309 - val_recall: 0.8454 - val_auc: 0.7395 - val_prc: 0.4378
Epoch 16/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6447 - tp: 652.0000 - fp: 1737.7500 - tn: 1710.7500 - fn: 199.5000 - accuracy: 0.5478 - precision: 0.2717 - recall: 0.7639 - auc: 0.6925 - prc: 0.3497 - val_loss: 0.6470 - val_tp: 267.0000 - val_fp: 533.0000 - val_tn: 550.0000 - val_fn: 50.0000 - val_accuracy: 0.5836 - val_precision: 0.3338 - val_recall: 0.8423 - val_auc: 0.7417 - val_prc: 0.4378
Epoch 17/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6435 - tp: 644.0000 - fp: 1704.0000 - tn: 1749.0000 - fn: 203.0000 - accuracy: 0.5551 - precision: 0.2727 - recall: 0.7585 - auc: 0.6890 - prc: 0.3407 - val_loss: 0.6446 - val_tp: 267.0000 - val_fp: 529.0000 - val_tn: 554.0000 - val_fn: 50.0000 - val_accuracy: 0.5864 - val_precision: 0.3354 - val_recall: 0.8423 - val_auc: 0.7439 - val_prc: 0.4437
Epoch 18/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6439 - tp: 655.2500 - fp: 1754.2500 - tn: 1699.5000 - fn: 191.0000 - accuracy: 0.5466 - precision: 0.2702 - recall: 0.7746 - auc: 0.6862 - prc: 0.3316 - val_loss: 0.6437 - val_tp: 267.0000 - val_fp: 527.0000 - val_tn: 556.0000 - val_fn: 50.0000 - val_accuracy: 0.5879 - val_precision: 0.3363 - val_recall: 0.8423 - val_auc: 0.7460 - val_prc: 0.4443
Epoch 19/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6344 - tp: 660.7500 - fp: 1722.2500 - tn: 1727.5000 - fn: 189.5000 - accuracy: 0.5569 - precision: 0.2784 - recall: 0.7786 - auc: 0.7066 - prc: 0.3568 - val_loss: 0.6426 - val_tp: 267.0000 - val_fp: 526.0000 - val_tn: 557.0000 - val_fn: 50.0000 - val_accuracy: 0.5886 - val_precision: 0.3367 - val_recall: 0.8423 - val_auc: 0.7484 - val_prc: 0.4499
Epoch 20/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6364 - tp: 661.0000 - fp: 1706.0000 - tn: 1733.2500 - fn: 199.7500 - accuracy: 0.5592 - precision: 0.2825 - recall: 0.7683 - auc: 0.7038 - prc: 0.3495 - val_loss: 0.6426 - val_tp: 266.0000 - val_fp: 525.0000 - val_tn: 558.0000 - val_fn: 51.0000 - val_accuracy: 0.5886 - val_precision: 0.3363 - val_recall: 0.8391 - val_auc: 0.7504 - val_prc: 0.4517
Epoch 21/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6292 - tp: 672.5000 - fp: 1705.0000 - tn: 1748.2500 - fn: 174.2500 - accuracy: 0.5634 - precision: 0.2828 - recall: 0.7949 - auc: 0.7075 - prc: 0.3655 - val_loss: 0.6413 - val_tp: 266.0000 - val_fp: 523.0000 - val_tn: 560.0000 - val_fn: 51.0000 - val_accuracy: 0.5900 - val_precision: 0.3371 - val_recall: 0.8391 - val_auc: 0.7521 - val_prc: 0.4563
Epoch 22/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6346 - tp: 679.0000 - fp: 1716.0000 - tn: 1729.0000 - fn: 176.0000 - accuracy: 0.5599 - precision: 0.2838 - recall: 0.7924 - auc: 0.7015 - prc: 0.3425 - val_loss: 0.6399 - val_tp: 265.0000 - val_fp: 521.0000 - val_tn: 562.0000 - val_fn: 52.0000 - val_accuracy: 0.5907 - val_precision: 0.3372 - val_recall: 0.8360 - val_auc: 0.7542 - val_prc: 0.4605
Epoch 23/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6239 - tp: 685.7500 - fp: 1668.0000 - tn: 1775.0000 - fn: 171.2500 - accuracy: 0.5733 - precision: 0.2931 - recall: 0.7985 - auc: 0.7222 - prc: 0.3792 - val_loss: 0.6360 - val_tp: 263.0000 - val_fp: 516.0000 - val_tn: 567.0000 - val_fn: 54.0000 - val_accuracy: 0.5929 - val_precision: 0.3376 - val_recall: 0.8297 - val_auc: 0.7551 - val_prc: 0.4606
Epoch 24/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6219 - tp: 677.7500 - fp: 1694.7500 - tn: 1753.2500 - fn: 174.2500 - accuracy: 0.5650 - precision: 0.2860 - recall: 0.7979 - auc: 0.7214 - prc: 0.3693 - val_loss: 0.6306 - val_tp: 262.0000 - val_fp: 506.0000 - val_tn: 577.0000 - val_fn: 55.0000 - val_accuracy: 0.5993 - val_precision: 0.3411 - val_recall: 0.8265 - val_auc: 0.7572 - val_prc: 0.4638
Epoch 25/200
3/3 [==============================] - 0s 21ms/step - loss: 0.6266 - tp: 685.2500 - fp: 1651.2500 - tn: 1792.7500 - fn: 170.7500 - accuracy: 0.5755 - precision: 0.2929 - recall: 0.8007 - auc: 0.7118 - prc: 0.3549 - val_loss: 0.6259 - val_tp: 261.0000 - val_fp: 495.0000 - val_tn: 588.0000 - val_fn: 56.0000 - val_accuracy: 0.6064 - val_precision: 0.3452 - val_recall: 0.8233 - val_auc: 0.7580 - val_prc: 0.4682
Epoch 26/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6242 - tp: 666.7500 - fp: 1613.2500 - tn: 1829.5000 - fn: 190.5000 - accuracy: 0.5789 - precision: 0.2916 - recall: 0.7781 - auc: 0.7186 - prc: 0.3734 - val_loss: 0.6205 - val_tp: 261.0000 - val_fp: 484.0000 - val_tn: 599.0000 - val_fn: 56.0000 - val_accuracy: 0.6143 - val_precision: 0.3503 - val_recall: 0.8233 - val_auc: 0.7592 - val_prc: 0.4701
Epoch 27/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6150 - tp: 658.7500 - fp: 1586.5000 - tn: 1874.7500 - fn: 180.0000 - accuracy: 0.5877 - precision: 0.2901 - recall: 0.7889 - auc: 0.7250 - prc: 0.3786 - val_loss: 0.6156 - val_tp: 257.0000 - val_fp: 478.0000 - val_tn: 605.0000 - val_fn: 60.0000 - val_accuracy: 0.6157 - val_precision: 0.3497 - val_recall: 0.8107 - val_auc: 0.7604 - val_prc: 0.4758
Epoch 28/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6125 - tp: 669.2500 - fp: 1537.7500 - tn: 1911.7500 - fn: 181.2500 - accuracy: 0.6010 - precision: 0.3031 - recall: 0.7879 - auc: 0.7329 - prc: 0.3806 - val_loss: 0.6133 - val_tp: 256.0000 - val_fp: 469.0000 - val_tn: 614.0000 - val_fn: 61.0000 - val_accuracy: 0.6214 - val_precision: 0.3531 - val_recall: 0.8076 - val_auc: 0.7612 - val_prc: 0.4776
Epoch 29/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6186 - tp: 680.5000 - fp: 1560.7500 - tn: 1882.0000 - fn: 176.7500 - accuracy: 0.5959 - precision: 0.3047 - recall: 0.7962 - auc: 0.7264 - prc: 0.3708 - val_loss: 0.6119 - val_tp: 256.0000 - val_fp: 466.0000 - val_tn: 617.0000 - val_fn: 61.0000 - val_accuracy: 0.6236 - val_precision: 0.3546 - val_recall: 0.8076 - val_auc: 0.7627 - val_prc: 0.4825
Epoch 30/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6158 - tp: 676.0000 - fp: 1562.2500 - tn: 1879.5000 - fn: 182.2500 - accuracy: 0.5946 - precision: 0.3028 - recall: 0.7858 - auc: 0.7365 - prc: 0.3950 - val_loss: 0.6120 - val_tp: 257.0000 - val_fp: 467.0000 - val_tn: 616.0000 - val_fn: 60.0000 - val_accuracy: 0.6236 - val_precision: 0.3550 - val_recall: 0.8107 - val_auc: 0.7644 - val_prc: 0.4889
Epoch 31/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6163 - tp: 670.0000 - fp: 1525.5000 - tn: 1923.2500 - fn: 181.2500 - accuracy: 0.6031 - precision: 0.3058 - recall: 0.7861 - auc: 0.7349 - prc: 0.3937 - val_loss: 0.6109 - val_tp: 258.0000 - val_fp: 463.0000 - val_tn: 620.0000 - val_fn: 59.0000 - val_accuracy: 0.6271 - val_precision: 0.3578 - val_recall: 0.8139 - val_auc: 0.7656 - val_prc: 0.4931
Epoch 32/200
3/3 [==============================] - 0s 15ms/step - loss: 0.6077 - tp: 669.7500 - fp: 1546.0000 - tn: 1903.0000 - fn: 181.2500 - accuracy: 0.5998 - precision: 0.3037 - recall: 0.7897 - auc: 0.7409 - prc: 0.4003 - val_loss: 0.6087 - val_tp: 258.0000 - val_fp: 459.0000 - val_tn: 624.0000 - val_fn: 59.0000 - val_accuracy: 0.6300 - val_precision: 0.3598 - val_recall: 0.8139 - val_auc: 0.7666 - val_prc: 0.4950
Epoch 33/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6084 - tp: 659.2500 - fp: 1520.7500 - tn: 1933.2500 - fn: 186.7500 - accuracy: 0.6018 - precision: 0.3015 - recall: 0.7771 - auc: 0.7339 - prc: 0.4056 - val_loss: 0.6058 - val_tp: 256.0000 - val_fp: 451.0000 - val_tn: 632.0000 - val_fn: 61.0000 - val_accuracy: 0.6343 - val_precision: 0.3621 - val_recall: 0.8076 - val_auc: 0.7676 - val_prc: 0.4999
Epoch 34/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6111 - tp: 677.2500 - fp: 1509.5000 - tn: 1935.5000 - fn: 177.7500 - accuracy: 0.6067 - precision: 0.3101 - recall: 0.7915 - auc: 0.7376 - prc: 0.3971 - val_loss: 0.6051 - val_tp: 254.0000 - val_fp: 450.0000 - val_tn: 633.0000 - val_fn: 63.0000 - val_accuracy: 0.6336 - val_precision: 0.3608 - val_recall: 0.8013 - val_auc: 0.7681 - val_prc: 0.4998
Epoch 35/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6165 - tp: 650.7500 - fp: 1479.5000 - tn: 1969.0000 - fn: 200.7500 - accuracy: 0.6079 - precision: 0.3042 - recall: 0.7621 - auc: 0.7300 - prc: 0.4163 - val_loss: 0.6055 - val_tp: 254.0000 - val_fp: 451.0000 - val_tn: 632.0000 - val_fn: 63.0000 - val_accuracy: 0.6329 - val_precision: 0.3603 - val_recall: 0.8013 - val_auc: 0.7693 - val_prc: 0.5031
Epoch 36/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6048 - tp: 659.7500 - fp: 1480.0000 - tn: 1973.7500 - fn: 186.5000 - accuracy: 0.6136 - precision: 0.3087 - recall: 0.7823 - auc: 0.7398 - prc: 0.3983 - val_loss: 0.6046 - val_tp: 254.0000 - val_fp: 445.0000 - val_tn: 638.0000 - val_fn: 63.0000 - val_accuracy: 0.6371 - val_precision: 0.3634 - val_recall: 0.8013 - val_auc: 0.7704 - val_prc: 0.5050
Epoch 37/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6023 - tp: 677.0000 - fp: 1505.7500 - tn: 1947.7500 - fn: 169.5000 - accuracy: 0.6115 - precision: 0.3109 - recall: 0.7999 - auc: 0.7510 - prc: 0.4093 - val_loss: 0.6024 - val_tp: 252.0000 - val_fp: 440.0000 - val_tn: 643.0000 - val_fn: 65.0000 - val_accuracy: 0.6393 - val_precision: 0.3642 - val_recall: 0.7950 - val_auc: 0.7706 - val_prc: 0.5047
Epoch 38/200
3/3 [==============================] - 0s 15ms/step - loss: 0.6017 - tp: 665.2500 - fp: 1442.5000 - tn: 2009.0000 - fn: 183.2500 - accuracy: 0.6223 - precision: 0.3149 - recall: 0.7839 - auc: 0.7452 - prc: 0.4254 - val_loss: 0.6007 - val_tp: 251.0000 - val_fp: 433.0000 - val_tn: 650.0000 - val_fn: 66.0000 - val_accuracy: 0.6436 - val_precision: 0.3670 - val_recall: 0.7918 - val_auc: 0.7715 - val_prc: 0.5075
Epoch 39/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6050 - tp: 673.2500 - fp: 1467.0000 - tn: 1976.5000 - fn: 183.2500 - accuracy: 0.6170 - precision: 0.3163 - recall: 0.7869 - auc: 0.7472 - prc: 0.4343 - val_loss: 0.6008 - val_tp: 252.0000 - val_fp: 430.0000 - val_tn: 653.0000 - val_fn: 65.0000 - val_accuracy: 0.6464 - val_precision: 0.3695 - val_recall: 0.7950 - val_auc: 0.7726 - val_prc: 0.5099
Epoch 40/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5926 - tp: 680.2500 - fp: 1482.5000 - tn: 1965.5000 - fn: 171.7500 - accuracy: 0.6156 - precision: 0.3157 - recall: 0.8025 - auc: 0.7554 - prc: 0.4207 - val_loss: 0.5981 - val_tp: 251.0000 - val_fp: 421.0000 - val_tn: 662.0000 - val_fn: 66.0000 - val_accuracy: 0.6521 - val_precision: 0.3735 - val_recall: 0.7918 - val_auc: 0.7733 - val_prc: 0.5111
Epoch 41/200
3/3 [==============================] - 0s 15ms/step - loss: 0.6056 - tp: 668.2500 - fp: 1419.7500 - tn: 2028.2500 - fn: 183.7500 - accuracy: 0.6287 - precision: 0.3208 - recall: 0.7815 - auc: 0.7473 - prc: 0.4122 - val_loss: 0.5972 - val_tp: 250.0000 - val_fp: 419.0000 - val_tn: 664.0000 - val_fn: 67.0000 - val_accuracy: 0.6529 - val_precision: 0.3737 - val_recall: 0.7886 - val_auc: 0.7747 - val_prc: 0.5150
Epoch 42/200
3/3 [==============================] - 0s 15ms/step - loss: 0.6043 - tp: 668.7500 - fp: 1442.0000 - tn: 2000.2500 - fn: 189.0000 - accuracy: 0.6188 - precision: 0.3164 - recall: 0.7790 - auc: 0.7492 - prc: 0.4159 - val_loss: 0.5954 - val_tp: 250.0000 - val_fp: 417.0000 - val_tn: 666.0000 - val_fn: 67.0000 - val_accuracy: 0.6543 - val_precision: 0.3748 - val_recall: 0.7886 - val_auc: 0.7756 - val_prc: 0.5176
Epoch 43/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5940 - tp: 674.0000 - fp: 1467.5000 - tn: 1981.5000 - fn: 177.0000 - accuracy: 0.6167 - precision: 0.3148 - recall: 0.7960 - auc: 0.7573 - prc: 0.4277 - val_loss: 0.5914 - val_tp: 249.0000 - val_fp: 407.0000 - val_tn: 676.0000 - val_fn: 68.0000 - val_accuracy: 0.6607 - val_precision: 0.3796 - val_recall: 0.7855 - val_auc: 0.7766 - val_prc: 0.5195
Epoch 44/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5881 - tp: 656.0000 - fp: 1397.0000 - tn: 2047.2500 - fn: 199.7500 - accuracy: 0.6301 - precision: 0.3203 - recall: 0.7665 - auc: 0.7584 - prc: 0.4286 - val_loss: 0.5891 - val_tp: 247.0000 - val_fp: 402.0000 - val_tn: 681.0000 - val_fn: 70.0000 - val_accuracy: 0.6629 - val_precision: 0.3806 - val_recall: 0.7792 - val_auc: 0.7772 - val_prc: 0.5208
Epoch 45/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5822 - tp: 681.2500 - fp: 1377.0000 - tn: 2065.0000 - fn: 176.7500 - accuracy: 0.6400 - precision: 0.3340 - recall: 0.7992 - auc: 0.7671 - prc: 0.4503 - val_loss: 0.5854 - val_tp: 244.0000 - val_fp: 391.0000 - val_tn: 692.0000 - val_fn: 73.0000 - val_accuracy: 0.6686 - val_precision: 0.3843 - val_recall: 0.7697 - val_auc: 0.7782 - val_prc: 0.5230
Epoch 46/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5803 - tp: 647.2500 - fp: 1366.7500 - tn: 2084.5000 - fn: 201.5000 - accuracy: 0.6339 - precision: 0.3203 - recall: 0.7644 - auc: 0.7616 - prc: 0.4435 - val_loss: 0.5809 - val_tp: 242.0000 - val_fp: 381.0000 - val_tn: 702.0000 - val_fn: 75.0000 - val_accuracy: 0.6743 - val_precision: 0.3884 - val_recall: 0.7634 - val_auc: 0.7791 - val_prc: 0.5241
Epoch 47/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5896 - tp: 657.2500 - fp: 1344.2500 - tn: 2106.2500 - fn: 192.2500 - accuracy: 0.6428 - precision: 0.3281 - recall: 0.7735 - auc: 0.7559 - prc: 0.4333 - val_loss: 0.5774 - val_tp: 241.0000 - val_fp: 372.0000 - val_tn: 711.0000 - val_fn: 76.0000 - val_accuracy: 0.6800 - val_precision: 0.3931 - val_recall: 0.7603 - val_auc: 0.7797 - val_prc: 0.5272
Epoch 48/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5995 - tp: 656.7500 - fp: 1322.5000 - tn: 2114.7500 - fn: 206.0000 - accuracy: 0.6443 - precision: 0.3336 - recall: 0.7593 - auc: 0.7510 - prc: 0.4401 - val_loss: 0.5759 - val_tp: 242.0000 - val_fp: 369.0000 - val_tn: 714.0000 - val_fn: 75.0000 - val_accuracy: 0.6829 - val_precision: 0.3961 - val_recall: 0.7634 - val_auc: 0.7810 - val_prc: 0.5295
Epoch 49/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5836 - tp: 652.0000 - fp: 1257.2500 - tn: 2186.5000 - fn: 204.2500 - accuracy: 0.6606 - precision: 0.3417 - recall: 0.7590 - auc: 0.7639 - prc: 0.4531 - val_loss: 0.5754 - val_tp: 242.0000 - val_fp: 369.0000 - val_tn: 714.0000 - val_fn: 75.0000 - val_accuracy: 0.6829 - val_precision: 0.3961 - val_recall: 0.7634 - val_auc: 0.7815 - val_prc: 0.5318
Epoch 50/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5849 - tp: 644.2500 - fp: 1307.2500 - tn: 2145.5000 - fn: 203.0000 - accuracy: 0.6509 - precision: 0.3312 - recall: 0.7614 - auc: 0.7639 - prc: 0.4504 - val_loss: 0.5751 - val_tp: 242.0000 - val_fp: 366.0000 - val_tn: 717.0000 - val_fn: 75.0000 - val_accuracy: 0.6850 - val_precision: 0.3980 - val_recall: 0.7634 - val_auc: 0.7823 - val_prc: 0.5334
Epoch 51/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5853 - tp: 666.7500 - fp: 1286.2500 - tn: 2162.0000 - fn: 185.0000 - accuracy: 0.6592 - precision: 0.3416 - recall: 0.7865 - auc: 0.7732 - prc: 0.4592 - val_loss: 0.5765 - val_tp: 243.0000 - val_fp: 368.0000 - val_tn: 715.0000 - val_fn: 74.0000 - val_accuracy: 0.6843 - val_precision: 0.3977 - val_recall: 0.7666 - val_auc: 0.7836 - val_prc: 0.5374
Epoch 52/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5851 - tp: 666.0000 - fp: 1336.5000 - tn: 2113.2500 - fn: 184.2500 - accuracy: 0.6470 - precision: 0.3340 - recall: 0.7879 - auc: 0.7663 - prc: 0.4441 - val_loss: 0.5765 - val_tp: 243.0000 - val_fp: 368.0000 - val_tn: 715.0000 - val_fn: 74.0000 - val_accuracy: 0.6843 - val_precision: 0.3977 - val_recall: 0.7666 - val_auc: 0.7851 - val_prc: 0.5406
Epoch 53/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5926 - tp: 665.5000 - fp: 1344.2500 - tn: 2099.0000 - fn: 191.2500 - accuracy: 0.6435 - precision: 0.3328 - recall: 0.7776 - auc: 0.7642 - prc: 0.4769 - val_loss: 0.5777 - val_tp: 245.0000 - val_fp: 370.0000 - val_tn: 713.0000 - val_fn: 72.0000 - val_accuracy: 0.6843 - val_precision: 0.3984 - val_recall: 0.7729 - val_auc: 0.7863 - val_prc: 0.5440
Epoch 54/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5853 - tp: 676.0000 - fp: 1361.7500 - tn: 2087.2500 - fn: 175.0000 - accuracy: 0.6423 - precision: 0.3321 - recall: 0.7914 - auc: 0.7682 - prc: 0.4562 - val_loss: 0.5759 - val_tp: 244.0000 - val_fp: 366.0000 - val_tn: 717.0000 - val_fn: 73.0000 - val_accuracy: 0.6864 - val_precision: 0.4000 - val_recall: 0.7697 - val_auc: 0.7872 - val_prc: 0.5460
Epoch 55/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5777 - tp: 651.5000 - fp: 1298.0000 - tn: 2159.5000 - fn: 191.0000 - accuracy: 0.6532 - precision: 0.3321 - recall: 0.7715 - auc: 0.7657 - prc: 0.4500 - val_loss: 0.5725 - val_tp: 244.0000 - val_fp: 357.0000 - val_tn: 726.0000 - val_fn: 73.0000 - val_accuracy: 0.6929 - val_precision: 0.4060 - val_recall: 0.7697 - val_auc: 0.7886 - val_prc: 0.5500
Epoch 56/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5832 - tp: 668.5000 - fp: 1291.7500 - tn: 2152.0000 - fn: 187.7500 - accuracy: 0.6557 - precision: 0.3413 - recall: 0.7818 - auc: 0.7668 - prc: 0.4584 - val_loss: 0.5692 - val_tp: 243.0000 - val_fp: 352.0000 - val_tn: 731.0000 - val_fn: 74.0000 - val_accuracy: 0.6957 - val_precision: 0.4084 - val_recall: 0.7666 - val_auc: 0.7896 - val_prc: 0.5520
Epoch 57/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5832 - tp: 658.5000 - fp: 1278.2500 - tn: 2168.2500 - fn: 195.0000 - accuracy: 0.6565 - precision: 0.3401 - recall: 0.7713 - auc: 0.7679 - prc: 0.4660 - val_loss: 0.5653 - val_tp: 242.0000 - val_fp: 346.0000 - val_tn: 737.0000 - val_fn: 75.0000 - val_accuracy: 0.6993 - val_precision: 0.4116 - val_recall: 0.7634 - val_auc: 0.7904 - val_prc: 0.5541
Epoch 58/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5644 - tp: 667.5000 - fp: 1238.2500 - tn: 2214.2500 - fn: 180.0000 - accuracy: 0.6718 - precision: 0.3507 - recall: 0.7901 - auc: 0.7850 - prc: 0.4821 - val_loss: 0.5606 - val_tp: 239.0000 - val_fp: 334.0000 - val_tn: 749.0000 - val_fn: 78.0000 - val_accuracy: 0.7057 - val_precision: 0.4171 - val_recall: 0.7539 - val_auc: 0.7911 - val_prc: 0.5567
Epoch 59/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5761 - tp: 651.2500 - fp: 1254.2500 - tn: 2192.5000 - fn: 202.0000 - accuracy: 0.6599 - precision: 0.3400 - recall: 0.7614 - auc: 0.7684 - prc: 0.4672 - val_loss: 0.5581 - val_tp: 237.0000 - val_fp: 326.0000 - val_tn: 757.0000 - val_fn: 80.0000 - val_accuracy: 0.7100 - val_precision: 0.4210 - val_recall: 0.7476 - val_auc: 0.7924 - val_prc: 0.5596
Epoch 60/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5692 - tp: 641.5000 - fp: 1206.0000 - tn: 2250.5000 - fn: 202.0000 - accuracy: 0.6746 - precision: 0.3477 - recall: 0.7605 - auc: 0.7777 - prc: 0.4867 - val_loss: 0.5561 - val_tp: 237.0000 - val_fp: 320.0000 - val_tn: 763.0000 - val_fn: 80.0000 - val_accuracy: 0.7143 - val_precision: 0.4255 - val_recall: 0.7476 - val_auc: 0.7933 - val_prc: 0.5602
Epoch 61/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5743 - tp: 653.2500 - fp: 1208.5000 - tn: 2238.5000 - fn: 199.7500 - accuracy: 0.6721 - precision: 0.3511 - recall: 0.7643 - auc: 0.7772 - prc: 0.4840 - val_loss: 0.5558 - val_tp: 237.0000 - val_fp: 318.0000 - val_tn: 765.0000 - val_fn: 80.0000 - val_accuracy: 0.7157 - val_precision: 0.4270 - val_recall: 0.7476 - val_auc: 0.7943 - val_prc: 0.5623
Epoch 62/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5735 - tp: 667.0000 - fp: 1203.0000 - tn: 2232.7500 - fn: 197.2500 - accuracy: 0.6761 - precision: 0.3618 - recall: 0.7736 - auc: 0.7793 - prc: 0.4889 - val_loss: 0.5561 - val_tp: 238.0000 - val_fp: 318.0000 - val_tn: 765.0000 - val_fn: 79.0000 - val_accuracy: 0.7164 - val_precision: 0.4281 - val_recall: 0.7508 - val_auc: 0.7958 - val_prc: 0.5665
Epoch 63/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5666 - tp: 654.0000 - fp: 1235.0000 - tn: 2227.5000 - fn: 183.5000 - accuracy: 0.6710 - precision: 0.3445 - recall: 0.7799 - auc: 0.7816 - prc: 0.4896 - val_loss: 0.5562 - val_tp: 239.0000 - val_fp: 316.0000 - val_tn: 767.0000 - val_fn: 78.0000 - val_accuracy: 0.7186 - val_precision: 0.4306 - val_recall: 0.7539 - val_auc: 0.7971 - val_prc: 0.5682
Epoch 64/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5751 - tp: 640.0000 - fp: 1232.5000 - tn: 2225.5000 - fn: 202.0000 - accuracy: 0.6659 - precision: 0.3390 - recall: 0.7529 - auc: 0.7726 - prc: 0.4836 - val_loss: 0.5571 - val_tp: 239.0000 - val_fp: 316.0000 - val_tn: 767.0000 - val_fn: 78.0000 - val_accuracy: 0.7186 - val_precision: 0.4306 - val_recall: 0.7539 - val_auc: 0.7984 - val_prc: 0.5704
Epoch 65/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5612 - tp: 646.0000 - fp: 1202.0000 - tn: 2260.7500 - fn: 191.2500 - accuracy: 0.6778 - precision: 0.3490 - recall: 0.7772 - auc: 0.7842 - prc: 0.4796 - val_loss: 0.5557 - val_tp: 240.0000 - val_fp: 313.0000 - val_tn: 770.0000 - val_fn: 77.0000 - val_accuracy: 0.7214 - val_precision: 0.4340 - val_recall: 0.7571 - val_auc: 0.7998 - val_prc: 0.5742
Epoch 66/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5670 - tp: 654.2500 - fp: 1189.2500 - tn: 2268.5000 - fn: 188.0000 - accuracy: 0.6791 - precision: 0.3534 - recall: 0.7779 - auc: 0.7857 - prc: 0.4772 - val_loss: 0.5543 - val_tp: 241.0000 - val_fp: 310.0000 - val_tn: 773.0000 - val_fn: 76.0000 - val_accuracy: 0.7243 - val_precision: 0.4374 - val_recall: 0.7603 - val_auc: 0.8015 - val_prc: 0.5775
Epoch 67/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5683 - tp: 653.2500 - fp: 1192.2500 - tn: 2254.2500 - fn: 200.2500 - accuracy: 0.6769 - precision: 0.3557 - recall: 0.7653 - auc: 0.7826 - prc: 0.4958 - val_loss: 0.5534 - val_tp: 241.0000 - val_fp: 311.0000 - val_tn: 772.0000 - val_fn: 76.0000 - val_accuracy: 0.7236 - val_precision: 0.4366 - val_recall: 0.7603 - val_auc: 0.8028 - val_prc: 0.5798
Epoch 68/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5576 - tp: 653.7500 - fp: 1184.2500 - tn: 2269.7500 - fn: 192.2500 - accuracy: 0.6788 - precision: 0.3539 - recall: 0.7720 - auc: 0.7868 - prc: 0.5010 - val_loss: 0.5490 - val_tp: 237.0000 - val_fp: 303.0000 - val_tn: 780.0000 - val_fn: 80.0000 - val_accuracy: 0.7264 - val_precision: 0.4389 - val_recall: 0.7476 - val_auc: 0.8042 - val_prc: 0.5836
Epoch 69/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5580 - tp: 646.7500 - fp: 1169.2500 - tn: 2283.2500 - fn: 200.7500 - accuracy: 0.6829 - precision: 0.3581 - recall: 0.7698 - auc: 0.7884 - prc: 0.5021 - val_loss: 0.5446 - val_tp: 235.0000 - val_fp: 300.0000 - val_tn: 783.0000 - val_fn: 82.0000 - val_accuracy: 0.7271 - val_precision: 0.4393 - val_recall: 0.7413 - val_auc: 0.8055 - val_prc: 0.5865
Epoch 70/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5603 - tp: 640.2500 - fp: 1134.7500 - tn: 2315.5000 - fn: 209.5000 - accuracy: 0.6879 - precision: 0.3602 - recall: 0.7518 - auc: 0.7852 - prc: 0.5112 - val_loss: 0.5424 - val_tp: 235.0000 - val_fp: 290.0000 - val_tn: 793.0000 - val_fn: 82.0000 - val_accuracy: 0.7343 - val_precision: 0.4476 - val_recall: 0.7413 - val_auc: 0.8068 - val_prc: 0.5902
Epoch 71/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5599 - tp: 655.5000 - fp: 1138.5000 - tn: 2308.7500 - fn: 197.2500 - accuracy: 0.6907 - precision: 0.3679 - recall: 0.7722 - auc: 0.7905 - prc: 0.5072 - val_loss: 0.5404 - val_tp: 231.0000 - val_fp: 286.0000 - val_tn: 797.0000 - val_fn: 86.0000 - val_accuracy: 0.7343 - val_precision: 0.4468 - val_recall: 0.7287 - val_auc: 0.8085 - val_prc: 0.5944
Epoch 72/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5638 - tp: 669.0000 - fp: 1114.0000 - tn: 2319.5000 - fn: 197.5000 - accuracy: 0.6951 - precision: 0.3775 - recall: 0.7736 - auc: 0.7940 - prc: 0.5244 - val_loss: 0.5390 - val_tp: 230.0000 - val_fp: 283.0000 - val_tn: 800.0000 - val_fn: 87.0000 - val_accuracy: 0.7357 - val_precision: 0.4483 - val_recall: 0.7256 - val_auc: 0.8102 - val_prc: 0.5973
Epoch 73/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5559 - tp: 655.5000 - fp: 1116.2500 - tn: 2327.2500 - fn: 201.0000 - accuracy: 0.6936 - precision: 0.3713 - recall: 0.7694 - auc: 0.7915 - prc: 0.5309 - val_loss: 0.5369 - val_tp: 228.0000 - val_fp: 276.0000 - val_tn: 807.0000 - val_fn: 89.0000 - val_accuracy: 0.7393 - val_precision: 0.4524 - val_recall: 0.7192 - val_auc: 0.8114 - val_prc: 0.5985
Epoch 74/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5600 - tp: 634.0000 - fp: 1136.7500 - tn: 2314.5000 - fn: 214.7500 - accuracy: 0.6836 - precision: 0.3548 - recall: 0.7419 - auc: 0.7842 - prc: 0.5038 - val_loss: 0.5356 - val_tp: 228.0000 - val_fp: 275.0000 - val_tn: 808.0000 - val_fn: 89.0000 - val_accuracy: 0.7400 - val_precision: 0.4533 - val_recall: 0.7192 - val_auc: 0.8129 - val_prc: 0.6011
Epoch 75/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5544 - tp: 625.0000 - fp: 1085.7500 - tn: 2369.5000 - fn: 219.7500 - accuracy: 0.6964 - precision: 0.3629 - recall: 0.7400 - auc: 0.7887 - prc: 0.5149 - val_loss: 0.5343 - val_tp: 229.0000 - val_fp: 273.0000 - val_tn: 810.0000 - val_fn: 88.0000 - val_accuracy: 0.7421 - val_precision: 0.4562 - val_recall: 0.7224 - val_auc: 0.8141 - val_prc: 0.6031
Epoch 76/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5460 - tp: 647.0000 - fp: 1084.5000 - tn: 2368.0000 - fn: 200.5000 - accuracy: 0.7021 - precision: 0.3737 - recall: 0.7670 - auc: 0.7998 - prc: 0.5130 - val_loss: 0.5322 - val_tp: 230.0000 - val_fp: 268.0000 - val_tn: 815.0000 - val_fn: 87.0000 - val_accuracy: 0.7464 - val_precision: 0.4618 - val_recall: 0.7256 - val_auc: 0.8155 - val_prc: 0.6064
Epoch 77/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5586 - tp: 646.7500 - fp: 1091.2500 - tn: 2348.7500 - fn: 213.2500 - accuracy: 0.6956 - precision: 0.3720 - recall: 0.7526 - auc: 0.7940 - prc: 0.5184 - val_loss: 0.5301 - val_tp: 231.0000 - val_fp: 264.0000 - val_tn: 819.0000 - val_fn: 86.0000 - val_accuracy: 0.7500 - val_precision: 0.4667 - val_recall: 0.7287 - val_auc: 0.8164 - val_prc: 0.6073
Epoch 78/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5616 - tp: 645.5000 - fp: 1066.0000 - tn: 2374.2500 - fn: 214.2500 - accuracy: 0.7023 - precision: 0.3791 - recall: 0.7497 - auc: 0.7899 - prc: 0.5239 - val_loss: 0.5294 - val_tp: 231.0000 - val_fp: 262.0000 - val_tn: 821.0000 - val_fn: 86.0000 - val_accuracy: 0.7514 - val_precision: 0.4686 - val_recall: 0.7287 - val_auc: 0.8176 - val_prc: 0.6095
Epoch 79/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5525 - tp: 644.7500 - fp: 1041.5000 - tn: 2401.0000 - fn: 212.7500 - accuracy: 0.7089 - precision: 0.3851 - recall: 0.7510 - auc: 0.7968 - prc: 0.5421 - val_loss: 0.5290 - val_tp: 234.0000 - val_fp: 263.0000 - val_tn: 820.0000 - val_fn: 83.0000 - val_accuracy: 0.7529 - val_precision: 0.4708 - val_recall: 0.7382 - val_auc: 0.8185 - val_prc: 0.6120
Epoch 80/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5464 - tp: 636.2500 - fp: 1049.0000 - tn: 2407.7500 - fn: 207.0000 - accuracy: 0.7091 - precision: 0.3754 - recall: 0.7518 - auc: 0.7955 - prc: 0.5260 - val_loss: 0.5262 - val_tp: 234.0000 - val_fp: 261.0000 - val_tn: 822.0000 - val_fn: 83.0000 - val_accuracy: 0.7543 - val_precision: 0.4727 - val_recall: 0.7382 - val_auc: 0.8199 - val_prc: 0.6146
Epoch 81/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5574 - tp: 625.0000 - fp: 1055.7500 - tn: 2406.5000 - fn: 212.7500 - accuracy: 0.7031 - precision: 0.3674 - recall: 0.7437 - auc: 0.7873 - prc: 0.5049 - val_loss: 0.5240 - val_tp: 235.0000 - val_fp: 258.0000 - val_tn: 825.0000 - val_fn: 82.0000 - val_accuracy: 0.7571 - val_precision: 0.4767 - val_recall: 0.7413 - val_auc: 0.8212 - val_prc: 0.6184
Epoch 82/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5423 - tp: 651.0000 - fp: 1010.7500 - tn: 2429.7500 - fn: 208.5000 - accuracy: 0.7192 - precision: 0.3973 - recall: 0.7572 - auc: 0.8070 - prc: 0.5530 - val_loss: 0.5239 - val_tp: 235.0000 - val_fp: 258.0000 - val_tn: 825.0000 - val_fn: 82.0000 - val_accuracy: 0.7571 - val_precision: 0.4767 - val_recall: 0.7413 - val_auc: 0.8224 - val_prc: 0.6212
Epoch 83/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5392 - tp: 648.5000 - fp: 1036.0000 - tn: 2413.0000 - fn: 202.5000 - accuracy: 0.7120 - precision: 0.3841 - recall: 0.7606 - auc: 0.8050 - prc: 0.5419 - val_loss: 0.5213 - val_tp: 235.0000 - val_fp: 251.0000 - val_tn: 832.0000 - val_fn: 82.0000 - val_accuracy: 0.7621 - val_precision: 0.4835 - val_recall: 0.7413 - val_auc: 0.8238 - val_prc: 0.6261
Epoch 84/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5377 - tp: 659.5000 - fp: 1012.7500 - tn: 2435.2500 - fn: 192.5000 - accuracy: 0.7202 - precision: 0.3967 - recall: 0.7743 - auc: 0.8107 - prc: 0.5559 - val_loss: 0.5169 - val_tp: 234.0000 - val_fp: 250.0000 - val_tn: 833.0000 - val_fn: 83.0000 - val_accuracy: 0.7621 - val_precision: 0.4835 - val_recall: 0.7382 - val_auc: 0.8247 - val_prc: 0.6281
Epoch 85/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5349 - tp: 641.5000 - fp: 978.5000 - tn: 2477.5000 - fn: 202.5000 - accuracy: 0.7264 - precision: 0.3954 - recall: 0.7667 - auc: 0.8127 - prc: 0.5573 - val_loss: 0.5135 - val_tp: 232.0000 - val_fp: 244.0000 - val_tn: 839.0000 - val_fn: 85.0000 - val_accuracy: 0.7650 - val_precision: 0.4874 - val_recall: 0.7319 - val_auc: 0.8258 - val_prc: 0.6306
Epoch 86/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5494 - tp: 629.7500 - fp: 995.7500 - tn: 2455.2500 - fn: 219.2500 - accuracy: 0.7170 - precision: 0.3860 - recall: 0.7404 - auc: 0.7963 - prc: 0.5376 - val_loss: 0.5127 - val_tp: 232.0000 - val_fp: 241.0000 - val_tn: 842.0000 - val_fn: 85.0000 - val_accuracy: 0.7671 - val_precision: 0.4905 - val_recall: 0.7319 - val_auc: 0.8272 - val_prc: 0.6336
Epoch 87/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5269 - tp: 640.5000 - fp: 1018.5000 - tn: 2439.2500 - fn: 201.7500 - accuracy: 0.7156 - precision: 0.3840 - recall: 0.7610 - auc: 0.8140 - prc: 0.5641 - val_loss: 0.5110 - val_tp: 228.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 89.0000 - val_accuracy: 0.7686 - val_precision: 0.4924 - val_recall: 0.7192 - val_auc: 0.8282 - val_prc: 0.6355
Epoch 88/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5558 - tp: 632.7500 - fp: 971.0000 - tn: 2481.7500 - fn: 214.5000 - accuracy: 0.7243 - precision: 0.3947 - recall: 0.7481 - auc: 0.7964 - prc: 0.5185 - val_loss: 0.5116 - val_tp: 228.0000 - val_fp: 238.0000 - val_tn: 845.0000 - val_fn: 89.0000 - val_accuracy: 0.7664 - val_precision: 0.4893 - val_recall: 0.7192 - val_auc: 0.8295 - val_prc: 0.6380
Epoch 89/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5464 - tp: 639.0000 - fp: 989.5000 - tn: 2450.7500 - fn: 220.7500 - accuracy: 0.7175 - precision: 0.3939 - recall: 0.7444 - auc: 0.8041 - prc: 0.5439 - val_loss: 0.5124 - val_tp: 228.0000 - val_fp: 241.0000 - val_tn: 842.0000 - val_fn: 89.0000 - val_accuracy: 0.7643 - val_precision: 0.4861 - val_recall: 0.7192 - val_auc: 0.8304 - val_prc: 0.6403
Epoch 90/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5562 - tp: 638.0000 - fp: 994.2500 - tn: 2455.5000 - fn: 212.2500 - accuracy: 0.7182 - precision: 0.3887 - recall: 0.7509 - auc: 0.7985 - prc: 0.5405 - val_loss: 0.5120 - val_tp: 230.0000 - val_fp: 239.0000 - val_tn: 844.0000 - val_fn: 87.0000 - val_accuracy: 0.7671 - val_precision: 0.4904 - val_recall: 0.7256 - val_auc: 0.8314 - val_prc: 0.6432
Epoch 91/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5438 - tp: 626.7500 - fp: 982.2500 - tn: 2470.2500 - fn: 220.7500 - accuracy: 0.7193 - precision: 0.3871 - recall: 0.7377 - auc: 0.8021 - prc: 0.5333 - val_loss: 0.5114 - val_tp: 230.0000 - val_fp: 237.0000 - val_tn: 846.0000 - val_fn: 87.0000 - val_accuracy: 0.7686 - val_precision: 0.4925 - val_recall: 0.7256 - val_auc: 0.8322 - val_prc: 0.6454
Epoch 92/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5361 - tp: 635.7500 - fp: 942.0000 - tn: 2506.0000 - fn: 216.2500 - accuracy: 0.7314 - precision: 0.4035 - recall: 0.7420 - auc: 0.8081 - prc: 0.5629 - val_loss: 0.5092 - val_tp: 230.0000 - val_fp: 233.0000 - val_tn: 850.0000 - val_fn: 87.0000 - val_accuracy: 0.7714 - val_precision: 0.4968 - val_recall: 0.7256 - val_auc: 0.8330 - val_prc: 0.6460
Epoch 93/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5334 - tp: 640.0000 - fp: 945.5000 - tn: 2502.0000 - fn: 212.5000 - accuracy: 0.7310 - precision: 0.4035 - recall: 0.7531 - auc: 0.8107 - prc: 0.5652 - val_loss: 0.5061 - val_tp: 227.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 90.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.7161 - val_auc: 0.8336 - val_prc: 0.6481
Epoch 94/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5419 - tp: 638.2500 - fp: 966.5000 - tn: 2474.5000 - fn: 220.7500 - accuracy: 0.7227 - precision: 0.3971 - recall: 0.7446 - auc: 0.8032 - prc: 0.5588 - val_loss: 0.5032 - val_tp: 226.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 91.0000 - val_accuracy: 0.7750 - val_precision: 0.5022 - val_recall: 0.7129 - val_auc: 0.8340 - val_prc: 0.6508
Epoch 95/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5299 - tp: 639.5000 - fp: 914.5000 - tn: 2528.7500 - fn: 217.2500 - accuracy: 0.7370 - precision: 0.4133 - recall: 0.7470 - auc: 0.8188 - prc: 0.5699 - val_loss: 0.5008 - val_tp: 225.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 92.0000 - val_accuracy: 0.7764 - val_precision: 0.5045 - val_recall: 0.7098 - val_auc: 0.8347 - val_prc: 0.6534
Epoch 96/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5439 - tp: 620.0000 - fp: 950.5000 - tn: 2499.5000 - fn: 230.0000 - accuracy: 0.7253 - precision: 0.3948 - recall: 0.7305 - auc: 0.8034 - prc: 0.5425 - val_loss: 0.4998 - val_tp: 225.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 92.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.7098 - val_auc: 0.8353 - val_prc: 0.6559
Epoch 97/200
3/3 [==============================] - 0s 24ms/step - loss: 0.5343 - tp: 625.2500 - fp: 913.0000 - tn: 2538.7500 - fn: 223.0000 - accuracy: 0.7361 - precision: 0.4042 - recall: 0.7370 - auc: 0.8096 - prc: 0.5495 - val_loss: 0.5002 - val_tp: 225.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 92.0000 - val_accuracy: 0.7750 - val_precision: 0.5022 - val_recall: 0.7098 - val_auc: 0.8361 - val_prc: 0.6591
Epoch 98/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5222 - tp: 663.0000 - fp: 932.0000 - tn: 2515.7500 - fn: 189.2500 - accuracy: 0.7395 - precision: 0.4160 - recall: 0.7832 - auc: 0.8218 - prc: 0.5637 - val_loss: 0.4976 - val_tp: 224.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 93.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.7066 - val_auc: 0.8364 - val_prc: 0.6602
Epoch 99/200
3/3 [==============================] - 0s 12ms/step - loss: 0.5269 - tp: 614.0000 - fp: 893.7500 - tn: 2570.5000 - fn: 221.7500 - accuracy: 0.7393 - precision: 0.4031 - recall: 0.7351 - auc: 0.8126 - prc: 0.5458 - val_loss: 0.4944 - val_tp: 223.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 94.0000 - val_accuracy: 0.7779 - val_precision: 0.5068 - val_recall: 0.7035 - val_auc: 0.8369 - val_prc: 0.6620
Epoch 100/200
3/3 [==============================] - 0s 11ms/step - loss: 0.5405 - tp: 629.2500 - fp: 892.2500 - tn: 2550.2500 - fn: 228.2500 - accuracy: 0.7386 - precision: 0.4144 - recall: 0.7301 - auc: 0.8055 - prc: 0.5636 - val_loss: 0.4944 - val_tp: 225.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 92.0000 - val_accuracy: 0.7786 - val_precision: 0.5079 - val_recall: 0.7098 - val_auc: 0.8375 - val_prc: 0.6623
Epoch 101/200
3/3 [==============================] - 0s 12ms/step - loss: 0.5340 - tp: 626.2500 - fp: 864.0000 - tn: 2577.2500 - fn: 232.5000 - accuracy: 0.7448 - precision: 0.4204 - recall: 0.7264 - auc: 0.8110 - prc: 0.5587 - val_loss: 0.4939 - val_tp: 225.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 92.0000 - val_accuracy: 0.7771 - val_precision: 0.5056 - val_recall: 0.7098 - val_auc: 0.8377 - val_prc: 0.6638
Epoch 102/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5224 - tp: 628.5000 - fp: 852.5000 - tn: 2594.5000 - fn: 224.5000 - accuracy: 0.7493 - precision: 0.4247 - recall: 0.7350 - auc: 0.8169 - prc: 0.5764 - val_loss: 0.4919 - val_tp: 224.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 93.0000 - val_accuracy: 0.7771 - val_precision: 0.5056 - val_recall: 0.7066 - val_auc: 0.8381 - val_prc: 0.6649
Epoch 103/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5311 - tp: 612.0000 - fp: 883.2500 - tn: 2566.0000 - fn: 238.7500 - accuracy: 0.7395 - precision: 0.4091 - recall: 0.7214 - auc: 0.8086 - prc: 0.5488 - val_loss: 0.4906 - val_tp: 225.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 92.0000 - val_accuracy: 0.7814 - val_precision: 0.5125 - val_recall: 0.7098 - val_auc: 0.8384 - val_prc: 0.6657
Epoch 104/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5375 - tp: 625.5000 - fp: 877.2500 - tn: 2562.7500 - fn: 234.5000 - accuracy: 0.7413 - precision: 0.4172 - recall: 0.7295 - auc: 0.8091 - prc: 0.5513 - val_loss: 0.4914 - val_tp: 227.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 90.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7161 - val_auc: 0.8392 - val_prc: 0.6674
Epoch 105/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5259 - tp: 628.7500 - fp: 864.0000 - tn: 2580.2500 - fn: 227.0000 - accuracy: 0.7458 - precision: 0.4217 - recall: 0.7327 - auc: 0.8160 - prc: 0.5642 - val_loss: 0.4917 - val_tp: 230.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 87.0000 - val_accuracy: 0.7771 - val_precision: 0.5055 - val_recall: 0.7256 - val_auc: 0.8395 - val_prc: 0.6679
Epoch 106/200
3/3 [==============================] - 0s 12ms/step - loss: 0.5267 - tp: 616.5000 - fp: 886.7500 - tn: 2570.5000 - fn: 226.2500 - accuracy: 0.7415 - precision: 0.4093 - recall: 0.7304 - auc: 0.8138 - prc: 0.5574 - val_loss: 0.4917 - val_tp: 231.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 86.0000 - val_accuracy: 0.7757 - val_precision: 0.5033 - val_recall: 0.7287 - val_auc: 0.8398 - val_prc: 0.6691
Epoch 107/200
3/3 [==============================] - 0s 12ms/step - loss: 0.5271 - tp: 630.2500 - fp: 859.2500 - tn: 2587.5000 - fn: 223.0000 - accuracy: 0.7477 - precision: 0.4208 - recall: 0.7366 - auc: 0.8150 - prc: 0.5710 - val_loss: 0.4939 - val_tp: 231.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 86.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.7287 - val_auc: 0.8402 - val_prc: 0.6692
Epoch 108/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5228 - tp: 635.2500 - fp: 897.2500 - tn: 2553.2500 - fn: 214.2500 - accuracy: 0.7421 - precision: 0.4150 - recall: 0.7490 - auc: 0.8170 - prc: 0.5588 - val_loss: 0.4944 - val_tp: 231.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 86.0000 - val_accuracy: 0.7729 - val_precision: 0.4989 - val_recall: 0.7287 - val_auc: 0.8405 - val_prc: 0.6705
Epoch 109/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5254 - tp: 629.5000 - fp: 873.0000 - tn: 2577.7500 - fn: 219.7500 - accuracy: 0.7468 - precision: 0.4187 - recall: 0.7426 - auc: 0.8169 - prc: 0.5618 - val_loss: 0.4935 - val_tp: 233.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 84.0000 - val_accuracy: 0.7750 - val_precision: 0.5022 - val_recall: 0.7350 - val_auc: 0.8409 - val_prc: 0.6718
Epoch 110/200
3/3 [==============================] - 0s 22ms/step - loss: 0.5305 - tp: 635.7500 - fp: 881.7500 - tn: 2558.7500 - fn: 223.7500 - accuracy: 0.7431 - precision: 0.4214 - recall: 0.7421 - auc: 0.8136 - prc: 0.5776 - val_loss: 0.4935 - val_tp: 233.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 84.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.7350 - val_auc: 0.8410 - val_prc: 0.6715
Epoch 111/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5148 - tp: 632.5000 - fp: 898.7500 - tn: 2557.2500 - fn: 211.5000 - accuracy: 0.7418 - precision: 0.4122 - recall: 0.7493 - auc: 0.8225 - prc: 0.5697 - val_loss: 0.4903 - val_tp: 232.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 85.0000 - val_accuracy: 0.7771 - val_precision: 0.5054 - val_recall: 0.7319 - val_auc: 0.8413 - val_prc: 0.6726
Epoch 112/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5313 - tp: 622.5000 - fp: 884.5000 - tn: 2560.0000 - fn: 233.0000 - accuracy: 0.7414 - precision: 0.4160 - recall: 0.7293 - auc: 0.8099 - prc: 0.5768 - val_loss: 0.4893 - val_tp: 231.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 86.0000 - val_accuracy: 0.7779 - val_precision: 0.5066 - val_recall: 0.7287 - val_auc: 0.8413 - val_prc: 0.6720
Epoch 113/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5285 - tp: 627.7500 - fp: 859.0000 - tn: 2596.2500 - fn: 217.0000 - accuracy: 0.7479 - precision: 0.4177 - recall: 0.7402 - auc: 0.8121 - prc: 0.5543 - val_loss: 0.4871 - val_tp: 230.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 87.0000 - val_accuracy: 0.7829 - val_precision: 0.5145 - val_recall: 0.7256 - val_auc: 0.8410 - val_prc: 0.6716
Epoch 114/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5222 - tp: 625.2500 - fp: 874.5000 - tn: 2573.2500 - fn: 227.0000 - accuracy: 0.7426 - precision: 0.4158 - recall: 0.7326 - auc: 0.8182 - prc: 0.5677 - val_loss: 0.4860 - val_tp: 227.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 90.0000 - val_accuracy: 0.7807 - val_precision: 0.5113 - val_recall: 0.7161 - val_auc: 0.8410 - val_prc: 0.6712
Epoch 115/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5324 - tp: 636.5000 - fp: 832.5000 - tn: 2616.7500 - fn: 214.2500 - accuracy: 0.7541 - precision: 0.4313 - recall: 0.7466 - auc: 0.8132 - prc: 0.5684 - val_loss: 0.4858 - val_tp: 228.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 89.0000 - val_accuracy: 0.7807 - val_precision: 0.5112 - val_recall: 0.7192 - val_auc: 0.8410 - val_prc: 0.6719
Epoch 116/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5192 - tp: 641.2500 - fp: 863.0000 - tn: 2582.5000 - fn: 213.2500 - accuracy: 0.7485 - precision: 0.4252 - recall: 0.7537 - auc: 0.8233 - prc: 0.5951 - val_loss: 0.4860 - val_tp: 229.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 88.0000 - val_accuracy: 0.7807 - val_precision: 0.5112 - val_recall: 0.7224 - val_auc: 0.8410 - val_prc: 0.6733
Epoch 117/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5235 - tp: 628.7500 - fp: 858.5000 - tn: 2587.7500 - fn: 225.0000 - accuracy: 0.7485 - precision: 0.4243 - recall: 0.7398 - auc: 0.8161 - prc: 0.5611 - val_loss: 0.4857 - val_tp: 230.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 87.0000 - val_accuracy: 0.7793 - val_precision: 0.5088 - val_recall: 0.7256 - val_auc: 0.8416 - val_prc: 0.6769
Epoch 118/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5221 - tp: 630.0000 - fp: 861.0000 - tn: 2581.7500 - fn: 227.2500 - accuracy: 0.7475 - precision: 0.4249 - recall: 0.7387 - auc: 0.8205 - prc: 0.5905 - val_loss: 0.4853 - val_tp: 230.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 87.0000 - val_accuracy: 0.7779 - val_precision: 0.5066 - val_recall: 0.7256 - val_auc: 0.8419 - val_prc: 0.6786
Epoch 119/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5070 - tp: 643.5000 - fp: 824.7500 - tn: 2618.7500 - fn: 213.0000 - accuracy: 0.7605 - precision: 0.4421 - recall: 0.7554 - auc: 0.8298 - prc: 0.6098 - val_loss: 0.4851 - val_tp: 230.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 87.0000 - val_accuracy: 0.7771 - val_precision: 0.5055 - val_recall: 0.7256 - val_auc: 0.8422 - val_prc: 0.6801
Epoch 120/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5174 - tp: 626.7500 - fp: 852.7500 - tn: 2596.7500 - fn: 223.7500 - accuracy: 0.7503 - precision: 0.4226 - recall: 0.7344 - auc: 0.8173 - prc: 0.5872 - val_loss: 0.4838 - val_tp: 233.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 84.0000 - val_accuracy: 0.7807 - val_precision: 0.5110 - val_recall: 0.7350 - val_auc: 0.8428 - val_prc: 0.6806
Epoch 121/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5133 - tp: 627.2500 - fp: 811.2500 - tn: 2636.2500 - fn: 225.2500 - accuracy: 0.7584 - precision: 0.4342 - recall: 0.7332 - auc: 0.8252 - prc: 0.5820 - val_loss: 0.4816 - val_tp: 231.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 86.0000 - val_accuracy: 0.7821 - val_precision: 0.5133 - val_recall: 0.7287 - val_auc: 0.8431 - val_prc: 0.6805
Epoch 122/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5198 - tp: 623.2500 - fp: 848.0000 - tn: 2610.2500 - fn: 218.5000 - accuracy: 0.7492 - precision: 0.4172 - recall: 0.7413 - auc: 0.8163 - prc: 0.5647 - val_loss: 0.4794 - val_tp: 231.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 86.0000 - val_accuracy: 0.7850 - val_precision: 0.5179 - val_recall: 0.7287 - val_auc: 0.8437 - val_prc: 0.6811
Epoch 123/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5203 - tp: 624.7500 - fp: 838.7500 - tn: 2609.2500 - fn: 227.2500 - accuracy: 0.7514 - precision: 0.4263 - recall: 0.7315 - auc: 0.8214 - prc: 0.5752 - val_loss: 0.4785 - val_tp: 230.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 87.0000 - val_accuracy: 0.7843 - val_precision: 0.5169 - val_recall: 0.7256 - val_auc: 0.8438 - val_prc: 0.6825
Epoch 124/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5200 - tp: 627.5000 - fp: 837.5000 - tn: 2617.0000 - fn: 218.0000 - accuracy: 0.7547 - precision: 0.4268 - recall: 0.7451 - auc: 0.8218 - prc: 0.5944 - val_loss: 0.4790 - val_tp: 230.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 87.0000 - val_accuracy: 0.7843 - val_precision: 0.5169 - val_recall: 0.7256 - val_auc: 0.8443 - val_prc: 0.6838
Epoch 125/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5149 - tp: 618.5000 - fp: 832.2500 - tn: 2622.7500 - fn: 226.5000 - accuracy: 0.7531 - precision: 0.4245 - recall: 0.7330 - auc: 0.8195 - prc: 0.5825 - val_loss: 0.4802 - val_tp: 234.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 83.0000 - val_accuracy: 0.7843 - val_precision: 0.5166 - val_recall: 0.7382 - val_auc: 0.8444 - val_prc: 0.6845
Epoch 126/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5256 - tp: 627.0000 - fp: 827.0000 - tn: 2617.5000 - fn: 228.5000 - accuracy: 0.7550 - precision: 0.4322 - recall: 0.7312 - auc: 0.8174 - prc: 0.5762 - val_loss: 0.4832 - val_tp: 236.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 81.0000 - val_accuracy: 0.7836 - val_precision: 0.5153 - val_recall: 0.7445 - val_auc: 0.8444 - val_prc: 0.6849
Epoch 127/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5215 - tp: 610.7500 - fp: 861.2500 - tn: 2593.5000 - fn: 234.5000 - accuracy: 0.7433 - precision: 0.4110 - recall: 0.7167 - auc: 0.8161 - prc: 0.5762 - val_loss: 0.4853 - val_tp: 237.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 80.0000 - val_accuracy: 0.7779 - val_precision: 0.5064 - val_recall: 0.7476 - val_auc: 0.8442 - val_prc: 0.6838
Epoch 128/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5196 - tp: 630.7500 - fp: 850.2500 - tn: 2605.5000 - fn: 213.5000 - accuracy: 0.7539 - precision: 0.4256 - recall: 0.7459 - auc: 0.8181 - prc: 0.5833 - val_loss: 0.4869 - val_tp: 240.0000 - val_fp: 233.0000 - val_tn: 850.0000 - val_fn: 77.0000 - val_accuracy: 0.7786 - val_precision: 0.5074 - val_recall: 0.7571 - val_auc: 0.8440 - val_prc: 0.6830
Epoch 129/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5221 - tp: 640.7500 - fp: 859.0000 - tn: 2586.2500 - fn: 214.0000 - accuracy: 0.7486 - precision: 0.4255 - recall: 0.7496 - auc: 0.8190 - prc: 0.5918 - val_loss: 0.4889 - val_tp: 243.0000 - val_fp: 237.0000 - val_tn: 846.0000 - val_fn: 74.0000 - val_accuracy: 0.7779 - val_precision: 0.5063 - val_recall: 0.7666 - val_auc: 0.8442 - val_prc: 0.6838
Epoch 130/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5086 - tp: 657.0000 - fp: 885.2500 - tn: 2558.5000 - fn: 199.2500 - accuracy: 0.7466 - precision: 0.4255 - recall: 0.7657 - auc: 0.8289 - prc: 0.6064 - val_loss: 0.4882 - val_tp: 241.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 76.0000 - val_accuracy: 0.7779 - val_precision: 0.5063 - val_recall: 0.7603 - val_auc: 0.8440 - val_prc: 0.6836
Epoch 131/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5222 - tp: 634.7500 - fp: 847.7500 - tn: 2599.2500 - fn: 218.2500 - accuracy: 0.7516 - precision: 0.4278 - recall: 0.7425 - auc: 0.8199 - prc: 0.5871 - val_loss: 0.4848 - val_tp: 237.0000 - val_fp: 233.0000 - val_tn: 850.0000 - val_fn: 80.0000 - val_accuracy: 0.7764 - val_precision: 0.5043 - val_recall: 0.7476 - val_auc: 0.8440 - val_prc: 0.6831
Epoch 132/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5003 - tp: 656.0000 - fp: 827.7500 - tn: 2616.5000 - fn: 199.7500 - accuracy: 0.7607 - precision: 0.4423 - recall: 0.7672 - auc: 0.8356 - prc: 0.6136 - val_loss: 0.4796 - val_tp: 235.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 82.0000 - val_accuracy: 0.7793 - val_precision: 0.5087 - val_recall: 0.7413 - val_auc: 0.8440 - val_prc: 0.6833
Epoch 133/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5088 - tp: 639.7500 - fp: 806.7500 - tn: 2637.2500 - fn: 216.2500 - accuracy: 0.7600 - precision: 0.4406 - recall: 0.7480 - auc: 0.8290 - prc: 0.6183 - val_loss: 0.4752 - val_tp: 234.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 83.0000 - val_accuracy: 0.7800 - val_precision: 0.5098 - val_recall: 0.7382 - val_auc: 0.8440 - val_prc: 0.6833
Epoch 134/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5044 - tp: 634.2500 - fp: 820.7500 - tn: 2632.5000 - fn: 212.5000 - accuracy: 0.7588 - precision: 0.4343 - recall: 0.7500 - auc: 0.8312 - prc: 0.5899 - val_loss: 0.4724 - val_tp: 231.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 86.0000 - val_accuracy: 0.7807 - val_precision: 0.5111 - val_recall: 0.7287 - val_auc: 0.8441 - val_prc: 0.6833
Epoch 135/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5107 - tp: 622.0000 - fp: 757.7500 - tn: 2685.7500 - fn: 234.5000 - accuracy: 0.7718 - precision: 0.4563 - recall: 0.7287 - auc: 0.8312 - prc: 0.6079 - val_loss: 0.4714 - val_tp: 232.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 85.0000 - val_accuracy: 0.7814 - val_precision: 0.5121 - val_recall: 0.7319 - val_auc: 0.8444 - val_prc: 0.6829
Epoch 136/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5043 - tp: 631.0000 - fp: 751.0000 - tn: 2694.5000 - fn: 223.5000 - accuracy: 0.7744 - precision: 0.4594 - recall: 0.7438 - auc: 0.8357 - prc: 0.5872 - val_loss: 0.4701 - val_tp: 232.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 85.0000 - val_accuracy: 0.7814 - val_precision: 0.5121 - val_recall: 0.7319 - val_auc: 0.8445 - val_prc: 0.6837
Epoch 137/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5087 - tp: 622.0000 - fp: 808.0000 - tn: 2647.5000 - fn: 222.5000 - accuracy: 0.7600 - precision: 0.4317 - recall: 0.7351 - auc: 0.8260 - prc: 0.5837 - val_loss: 0.4698 - val_tp: 231.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 86.0000 - val_accuracy: 0.7821 - val_precision: 0.5133 - val_recall: 0.7287 - val_auc: 0.8449 - val_prc: 0.6846
Epoch 138/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5043 - tp: 614.7500 - fp: 785.7500 - tn: 2667.5000 - fn: 232.0000 - accuracy: 0.7644 - precision: 0.4398 - recall: 0.7287 - auc: 0.8304 - prc: 0.6060 - val_loss: 0.4716 - val_tp: 233.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 84.0000 - val_accuracy: 0.7821 - val_precision: 0.5132 - val_recall: 0.7350 - val_auc: 0.8449 - val_prc: 0.6853
Epoch 139/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5001 - tp: 635.0000 - fp: 802.5000 - tn: 2652.7500 - fn: 209.7500 - accuracy: 0.7655 - precision: 0.4411 - recall: 0.7524 - auc: 0.8342 - prc: 0.5975 - val_loss: 0.4738 - val_tp: 235.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 82.0000 - val_accuracy: 0.7821 - val_precision: 0.5131 - val_recall: 0.7413 - val_auc: 0.8455 - val_prc: 0.6858
Epoch 140/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5179 - tp: 624.5000 - fp: 828.0000 - tn: 2623.7500 - fn: 223.7500 - accuracy: 0.7546 - precision: 0.4282 - recall: 0.7349 - auc: 0.8229 - prc: 0.5873 - val_loss: 0.4762 - val_tp: 238.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 79.0000 - val_accuracy: 0.7807 - val_precision: 0.5107 - val_recall: 0.7508 - val_auc: 0.8458 - val_prc: 0.6867
Epoch 141/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5131 - tp: 640.2500 - fp: 835.5000 - tn: 2608.0000 - fn: 216.2500 - accuracy: 0.7549 - precision: 0.4346 - recall: 0.7481 - auc: 0.8259 - prc: 0.6019 - val_loss: 0.4776 - val_tp: 239.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 78.0000 - val_accuracy: 0.7800 - val_precision: 0.5096 - val_recall: 0.7539 - val_auc: 0.8463 - val_prc: 0.6871
Epoch 142/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5042 - tp: 650.7500 - fp: 836.7500 - tn: 2611.7500 - fn: 200.7500 - accuracy: 0.7595 - precision: 0.4382 - recall: 0.7649 - auc: 0.8340 - prc: 0.6089 - val_loss: 0.4780 - val_tp: 238.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 79.0000 - val_accuracy: 0.7807 - val_precision: 0.5107 - val_recall: 0.7508 - val_auc: 0.8466 - val_prc: 0.6871
Epoch 143/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5117 - tp: 650.0000 - fp: 835.5000 - tn: 2612.5000 - fn: 202.0000 - accuracy: 0.7596 - precision: 0.4390 - recall: 0.7638 - auc: 0.8299 - prc: 0.6087 - val_loss: 0.4768 - val_tp: 236.0000 - val_fp: 226.0000 - val_tn: 857.0000 - val_fn: 81.0000 - val_accuracy: 0.7807 - val_precision: 0.5108 - val_recall: 0.7445 - val_auc: 0.8466 - val_prc: 0.6872
Epoch 144/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5056 - tp: 620.2500 - fp: 843.7500 - tn: 2607.5000 - fn: 228.5000 - accuracy: 0.7497 - precision: 0.4211 - recall: 0.7288 - auc: 0.8264 - prc: 0.5976 - val_loss: 0.4752 - val_tp: 236.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 81.0000 - val_accuracy: 0.7814 - val_precision: 0.5119 - val_recall: 0.7445 - val_auc: 0.8466 - val_prc: 0.6874
Epoch 145/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5071 - tp: 630.2500 - fp: 819.7500 - tn: 2633.5000 - fn: 216.5000 - accuracy: 0.7587 - precision: 0.4327 - recall: 0.7421 - auc: 0.8279 - prc: 0.5856 - val_loss: 0.4725 - val_tp: 235.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 82.0000 - val_accuracy: 0.7829 - val_precision: 0.5142 - val_recall: 0.7413 - val_auc: 0.8468 - val_prc: 0.6870
Epoch 146/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5006 - tp: 628.7500 - fp: 786.5000 - tn: 2665.0000 - fn: 219.7500 - accuracy: 0.7671 - precision: 0.4454 - recall: 0.7436 - auc: 0.8342 - prc: 0.6052 - val_loss: 0.4708 - val_tp: 235.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 82.0000 - val_accuracy: 0.7821 - val_precision: 0.5131 - val_recall: 0.7413 - val_auc: 0.8468 - val_prc: 0.6874
Epoch 147/200
3/3 [==============================] - 0s 14ms/step - loss: 0.5083 - tp: 628.0000 - fp: 797.7500 - tn: 2651.7500 - fn: 222.5000 - accuracy: 0.7622 - precision: 0.4391 - recall: 0.7343 - auc: 0.8279 - prc: 0.6112 - val_loss: 0.4716 - val_tp: 236.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 81.0000 - val_accuracy: 0.7821 - val_precision: 0.5130 - val_recall: 0.7445 - val_auc: 0.8468 - val_prc: 0.6876
Epoch 148/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5150 - tp: 631.7500 - fp: 814.2500 - tn: 2629.7500 - fn: 224.2500 - accuracy: 0.7592 - precision: 0.4390 - recall: 0.7359 - auc: 0.8245 - prc: 0.5847 - val_loss: 0.4726 - val_tp: 238.0000 - val_fp: 226.0000 - val_tn: 857.0000 - val_fn: 79.0000 - val_accuracy: 0.7821 - val_precision: 0.5129 - val_recall: 0.7508 - val_auc: 0.8465 - val_prc: 0.6863
Epoch 149/200
3/3 [==============================] - 0s 15ms/step - loss: 0.4996 - tp: 624.0000 - fp: 821.0000 - tn: 2634.5000 - fn: 220.5000 - accuracy: 0.7569 - precision: 0.4285 - recall: 0.7336 - auc: 0.8326 - prc: 0.6067 - val_loss: 0.4738 - val_tp: 239.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 78.0000 - val_accuracy: 0.7807 - val_precision: 0.5107 - val_recall: 0.7539 - val_auc: 0.8464 - val_prc: 0.6866
Epoch 150/200
3/3 [==============================] - 0s 17ms/step - loss: 0.4981 - tp: 635.5000 - fp: 830.0000 - tn: 2616.2500 - fn: 218.2500 - accuracy: 0.7562 - precision: 0.4331 - recall: 0.7466 - auc: 0.8335 - prc: 0.6297 - val_loss: 0.4732 - val_tp: 239.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 78.0000 - val_accuracy: 0.7807 - val_precision: 0.5107 - val_recall: 0.7539 - val_auc: 0.8465 - val_prc: 0.6864
Epoch 151/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5108 - tp: 633.7500 - fp: 829.7500 - tn: 2626.2500 - fn: 210.2500 - accuracy: 0.7570 - precision: 0.4295 - recall: 0.7466 - auc: 0.8252 - prc: 0.5891 - val_loss: 0.4715 - val_tp: 239.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 78.0000 - val_accuracy: 0.7807 - val_precision: 0.5107 - val_recall: 0.7539 - val_auc: 0.8464 - val_prc: 0.6868
Epoch 152/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5075 - tp: 639.0000 - fp: 846.0000 - tn: 2604.7500 - fn: 210.2500 - accuracy: 0.7552 - precision: 0.4304 - recall: 0.7547 - auc: 0.8289 - prc: 0.5856 - val_loss: 0.4698 - val_tp: 237.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 80.0000 - val_accuracy: 0.7829 - val_precision: 0.5141 - val_recall: 0.7476 - val_auc: 0.8464 - val_prc: 0.6866
Epoch 153/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5095 - tp: 635.7500 - fp: 803.7500 - tn: 2649.7500 - fn: 210.7500 - accuracy: 0.7634 - precision: 0.4396 - recall: 0.7494 - auc: 0.8286 - prc: 0.5897 - val_loss: 0.4700 - val_tp: 237.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 80.0000 - val_accuracy: 0.7829 - val_precision: 0.5141 - val_recall: 0.7476 - val_auc: 0.8465 - val_prc: 0.6864
Epoch 154/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5214 - tp: 639.7500 - fp: 807.0000 - tn: 2639.5000 - fn: 213.7500 - accuracy: 0.7632 - precision: 0.4437 - recall: 0.7497 - auc: 0.8229 - prc: 0.5925 - val_loss: 0.4720 - val_tp: 239.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 78.0000 - val_accuracy: 0.7800 - val_precision: 0.5096 - val_recall: 0.7539 - val_auc: 0.8463 - val_prc: 0.6858
Epoch 155/200
3/3 [==============================] - 0s 22ms/step - loss: 0.5013 - tp: 634.5000 - fp: 781.5000 - tn: 2667.0000 - fn: 217.0000 - accuracy: 0.7675 - precision: 0.4471 - recall: 0.7410 - auc: 0.8312 - prc: 0.6100 - val_loss: 0.4734 - val_tp: 239.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 78.0000 - val_accuracy: 0.7771 - val_precision: 0.5053 - val_recall: 0.7539 - val_auc: 0.8466 - val_prc: 0.6858
Epoch 156/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5163 - tp: 635.7500 - fp: 823.5000 - tn: 2625.2500 - fn: 215.5000 - accuracy: 0.7580 - precision: 0.4359 - recall: 0.7464 - auc: 0.8248 - prc: 0.5917 - val_loss: 0.4741 - val_tp: 239.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 78.0000 - val_accuracy: 0.7771 - val_precision: 0.5053 - val_recall: 0.7539 - val_auc: 0.8464 - val_prc: 0.6855
Epoch 157/200
3/3 [==============================] - 0s 24ms/step - loss: 0.5022 - tp: 654.0000 - fp: 825.0000 - tn: 2619.2500 - fn: 201.7500 - accuracy: 0.7604 - precision: 0.4422 - recall: 0.7625 - auc: 0.8381 - prc: 0.5997 - val_loss: 0.4732 - val_tp: 240.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 77.0000 - val_accuracy: 0.7821 - val_precision: 0.5128 - val_recall: 0.7571 - val_auc: 0.8466 - val_prc: 0.6862
Epoch 158/200
3/3 [==============================] - 0s 23ms/step - loss: 0.5020 - tp: 629.0000 - fp: 802.0000 - tn: 2651.5000 - fn: 217.5000 - accuracy: 0.7627 - precision: 0.4367 - recall: 0.7431 - auc: 0.8297 - prc: 0.6044 - val_loss: 0.4712 - val_tp: 239.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 78.0000 - val_accuracy: 0.7821 - val_precision: 0.5129 - val_recall: 0.7539 - val_auc: 0.8465 - val_prc: 0.6860
Epoch 159/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5110 - tp: 623.0000 - fp: 818.5000 - tn: 2630.5000 - fn: 228.0000 - accuracy: 0.7565 - precision: 0.4315 - recall: 0.7337 - auc: 0.8286 - prc: 0.5976 - val_loss: 0.4697 - val_tp: 239.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 78.0000 - val_accuracy: 0.7850 - val_precision: 0.5173 - val_recall: 0.7539 - val_auc: 0.8466 - val_prc: 0.6850
Epoch 160/200
3/3 [==============================] - 0s 22ms/step - loss: 0.5057 - tp: 625.7500 - fp: 789.0000 - tn: 2656.0000 - fn: 229.2500 - accuracy: 0.7642 - precision: 0.4446 - recall: 0.7358 - auc: 0.8305 - prc: 0.6172 - val_loss: 0.4700 - val_tp: 238.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 79.0000 - val_accuracy: 0.7836 - val_precision: 0.5152 - val_recall: 0.7508 - val_auc: 0.8463 - val_prc: 0.6847
Epoch 161/200
3/3 [==============================] - 0s 19ms/step - loss: 0.4972 - tp: 647.2500 - fp: 770.7500 - tn: 2676.2500 - fn: 205.7500 - accuracy: 0.7737 - precision: 0.4590 - recall: 0.7577 - auc: 0.8405 - prc: 0.6123 - val_loss: 0.4704 - val_tp: 238.0000 - val_fp: 226.0000 - val_tn: 857.0000 - val_fn: 79.0000 - val_accuracy: 0.7821 - val_precision: 0.5129 - val_recall: 0.7508 - val_auc: 0.8462 - val_prc: 0.6841
Epoch 162/200
3/3 [==============================] - 0s 20ms/step - loss: 0.4961 - tp: 639.7500 - fp: 800.2500 - tn: 2652.0000 - fn: 208.0000 - accuracy: 0.7659 - precision: 0.4439 - recall: 0.7552 - auc: 0.8377 - prc: 0.6182 - val_loss: 0.4704 - val_tp: 238.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 79.0000 - val_accuracy: 0.7800 - val_precision: 0.5096 - val_recall: 0.7508 - val_auc: 0.8459 - val_prc: 0.6841
Epoch 163/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5141 - tp: 626.7500 - fp: 807.7500 - tn: 2636.2500 - fn: 229.2500 - accuracy: 0.7592 - precision: 0.4393 - recall: 0.7324 - auc: 0.8253 - prc: 0.5942 - val_loss: 0.4720 - val_tp: 239.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 78.0000 - val_accuracy: 0.7786 - val_precision: 0.5074 - val_recall: 0.7539 - val_auc: 0.8456 - val_prc: 0.6839
Epoch 164/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5058 - tp: 644.5000 - fp: 818.0000 - tn: 2624.5000 - fn: 213.0000 - accuracy: 0.7618 - precision: 0.4447 - recall: 0.7525 - auc: 0.8311 - prc: 0.6084 - val_loss: 0.4736 - val_tp: 241.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 76.0000 - val_accuracy: 0.7779 - val_precision: 0.5063 - val_recall: 0.7603 - val_auc: 0.8455 - val_prc: 0.6835
Epoch 165/200
3/3 [==============================] - 0s 21ms/step - loss: 0.4982 - tp: 633.2500 - fp: 788.5000 - tn: 2665.0000 - fn: 213.2500 - accuracy: 0.7686 - precision: 0.4455 - recall: 0.7480 - auc: 0.8384 - prc: 0.6038 - val_loss: 0.4729 - val_tp: 240.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 77.0000 - val_accuracy: 0.7779 - val_precision: 0.5063 - val_recall: 0.7571 - val_auc: 0.8457 - val_prc: 0.6844
Epoch 166/200
3/3 [==============================] - 0s 20ms/step - loss: 0.4860 - tp: 643.5000 - fp: 846.5000 - tn: 2611.0000 - fn: 199.0000 - accuracy: 0.7566 - precision: 0.4309 - recall: 0.7662 - auc: 0.8447 - prc: 0.6248 - val_loss: 0.4712 - val_tp: 240.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 77.0000 - val_accuracy: 0.7800 - val_precision: 0.5096 - val_recall: 0.7571 - val_auc: 0.8454 - val_prc: 0.6838
Epoch 167/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5062 - tp: 651.2500 - fp: 832.7500 - tn: 2608.2500 - fn: 207.7500 - accuracy: 0.7572 - precision: 0.4393 - recall: 0.7569 - auc: 0.8311 - prc: 0.6064 - val_loss: 0.4712 - val_tp: 241.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 76.0000 - val_accuracy: 0.7800 - val_precision: 0.5095 - val_recall: 0.7603 - val_auc: 0.8454 - val_prc: 0.6840
Epoch 168/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5090 - tp: 648.2500 - fp: 825.2500 - tn: 2617.0000 - fn: 209.5000 - accuracy: 0.7606 - precision: 0.4427 - recall: 0.7617 - auc: 0.8331 - prc: 0.5977 - val_loss: 0.4707 - val_tp: 241.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 76.0000 - val_accuracy: 0.7814 - val_precision: 0.5117 - val_recall: 0.7603 - val_auc: 0.8457 - val_prc: 0.6844
Epoch 169/200
3/3 [==============================] - 0s 18ms/step - loss: 0.4945 - tp: 631.2500 - fp: 812.5000 - tn: 2641.7500 - fn: 214.5000 - accuracy: 0.7618 - precision: 0.4368 - recall: 0.7428 - auc: 0.8340 - prc: 0.6103 - val_loss: 0.4702 - val_tp: 241.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 76.0000 - val_accuracy: 0.7807 - val_precision: 0.5106 - val_recall: 0.7603 - val_auc: 0.8457 - val_prc: 0.6848
Epoch 170/200
3/3 [==============================] - 0s 21ms/step - loss: 0.4930 - tp: 640.2500 - fp: 823.7500 - tn: 2626.7500 - fn: 209.2500 - accuracy: 0.7610 - precision: 0.4375 - recall: 0.7539 - auc: 0.8382 - prc: 0.6179 - val_loss: 0.4693 - val_tp: 239.0000 - val_fp: 233.0000 - val_tn: 850.0000 - val_fn: 78.0000 - val_accuracy: 0.7779 - val_precision: 0.5064 - val_recall: 0.7539 - val_auc: 0.8452 - val_prc: 0.6841
Epoch 171/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5049 - tp: 633.5000 - fp: 800.2500 - tn: 2638.5000 - fn: 227.7500 - accuracy: 0.7616 - precision: 0.4442 - recall: 0.7336 - auc: 0.8309 - prc: 0.6222 - val_loss: 0.4709 - val_tp: 239.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 78.0000 - val_accuracy: 0.7764 - val_precision: 0.5042 - val_recall: 0.7539 - val_auc: 0.8452 - val_prc: 0.6843
Epoch 172/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5011 - tp: 630.5000 - fp: 843.2500 - tn: 2612.0000 - fn: 214.2500 - accuracy: 0.7533 - precision: 0.4251 - recall: 0.7410 - auc: 0.8338 - prc: 0.6093 - val_loss: 0.4705 - val_tp: 239.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 78.0000 - val_accuracy: 0.7771 - val_precision: 0.5053 - val_recall: 0.7539 - val_auc: 0.8451 - val_prc: 0.6838
Epoch 173/200
3/3 [==============================] - 0s 14ms/step - loss: 0.4946 - tp: 652.5000 - fp: 824.0000 - tn: 2624.5000 - fn: 199.0000 - accuracy: 0.7641 - precision: 0.4439 - recall: 0.7680 - auc: 0.8398 - prc: 0.6200 - val_loss: 0.4702 - val_tp: 239.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 78.0000 - val_accuracy: 0.7771 - val_precision: 0.5053 - val_recall: 0.7539 - val_auc: 0.8452 - val_prc: 0.6836
Epoch 174/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5021 - tp: 632.2500 - fp: 802.7500 - tn: 2648.5000 - fn: 216.5000 - accuracy: 0.7640 - precision: 0.4400 - recall: 0.7447 - auc: 0.8323 - prc: 0.6130 - val_loss: 0.4694 - val_tp: 239.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 78.0000 - val_accuracy: 0.7793 - val_precision: 0.5085 - val_recall: 0.7539 - val_auc: 0.8453 - val_prc: 0.6840
Epoch 175/200
3/3 [==============================] - 0s 17ms/step - loss: 0.4993 - tp: 637.5000 - fp: 797.5000 - tn: 2641.0000 - fn: 224.0000 - accuracy: 0.7626 - precision: 0.4474 - recall: 0.7426 - auc: 0.8357 - prc: 0.6302 - val_loss: 0.4697 - val_tp: 239.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 78.0000 - val_accuracy: 0.7786 - val_precision: 0.5074 - val_recall: 0.7539 - val_auc: 0.8454 - val_prc: 0.6836
Epoch 176/200
3/3 [==============================] - 0s 18ms/step - loss: 0.4979 - tp: 635.5000 - fp: 796.2500 - tn: 2654.0000 - fn: 214.2500 - accuracy: 0.7652 - precision: 0.4431 - recall: 0.7492 - auc: 0.8333 - prc: 0.6023 - val_loss: 0.4683 - val_tp: 240.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 77.0000 - val_accuracy: 0.7814 - val_precision: 0.5117 - val_recall: 0.7571 - val_auc: 0.8454 - val_prc: 0.6836
Epoch 177/200
3/3 [==============================] - 0s 16ms/step - loss: 0.4885 - tp: 638.0000 - fp: 785.7500 - tn: 2666.2500 - fn: 210.0000 - accuracy: 0.7698 - precision: 0.4480 - recall: 0.7503 - auc: 0.8429 - prc: 0.6297 - val_loss: 0.4672 - val_tp: 240.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 77.0000 - val_accuracy: 0.7814 - val_precision: 0.5117 - val_recall: 0.7571 - val_auc: 0.8455 - val_prc: 0.6846
Epoch 178/200
3/3 [==============================] - 0s 17ms/step - loss: 0.4998 - tp: 652.2500 - fp: 826.2500 - tn: 2619.5000 - fn: 202.0000 - accuracy: 0.7604 - precision: 0.4413 - recall: 0.7680 - auc: 0.8378 - prc: 0.6222 - val_loss: 0.4667 - val_tp: 241.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 76.0000 - val_accuracy: 0.7829 - val_precision: 0.5139 - val_recall: 0.7603 - val_auc: 0.8458 - val_prc: 0.6852
Epoch 179/200
3/3 [==============================] - 0s 17ms/step - loss: 0.4951 - tp: 639.2500 - fp: 784.7500 - tn: 2663.0000 - fn: 213.0000 - accuracy: 0.7672 - precision: 0.4476 - recall: 0.7477 - auc: 0.8387 - prc: 0.6150 - val_loss: 0.4661 - val_tp: 241.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 76.0000 - val_accuracy: 0.7836 - val_precision: 0.5150 - val_recall: 0.7603 - val_auc: 0.8459 - val_prc: 0.6848
Epoch 180/200
3/3 [==============================] - 0s 15ms/step - loss: 0.4959 - tp: 631.2500 - fp: 790.7500 - tn: 2655.2500 - fn: 222.7500 - accuracy: 0.7650 - precision: 0.4443 - recall: 0.7395 - auc: 0.8361 - prc: 0.6160 - val_loss: 0.4661 - val_tp: 242.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 75.0000 - val_accuracy: 0.7836 - val_precision: 0.5149 - val_recall: 0.7634 - val_auc: 0.8457 - val_prc: 0.6840
Epoch 181/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5007 - tp: 636.7500 - fp: 812.5000 - tn: 2649.2500 - fn: 201.5000 - accuracy: 0.7647 - precision: 0.4378 - recall: 0.7602 - auc: 0.8353 - prc: 0.6092 - val_loss: 0.4665 - val_tp: 240.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 77.0000 - val_accuracy: 0.7814 - val_precision: 0.5117 - val_recall: 0.7571 - val_auc: 0.8457 - val_prc: 0.6843
Epoch 182/200
3/3 [==============================] - 0s 19ms/step - loss: 0.4998 - tp: 638.2500 - fp: 796.0000 - tn: 2654.7500 - fn: 211.0000 - accuracy: 0.7653 - precision: 0.4434 - recall: 0.7495 - auc: 0.8332 - prc: 0.6125 - val_loss: 0.4681 - val_tp: 239.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 78.0000 - val_accuracy: 0.7800 - val_precision: 0.5096 - val_recall: 0.7539 - val_auc: 0.8457 - val_prc: 0.6837
Epoch 183/200
3/3 [==============================] - 0s 13ms/step - loss: 0.5034 - tp: 647.0000 - fp: 821.7500 - tn: 2617.7500 - fn: 213.5000 - accuracy: 0.7579 - precision: 0.4403 - recall: 0.7502 - auc: 0.8348 - prc: 0.6133 - val_loss: 0.4690 - val_tp: 241.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 76.0000 - val_accuracy: 0.7836 - val_precision: 0.5150 - val_recall: 0.7603 - val_auc: 0.8455 - val_prc: 0.6824
Epoch 184/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5053 - tp: 643.0000 - fp: 816.7500 - tn: 2630.0000 - fn: 210.2500 - accuracy: 0.7621 - precision: 0.4424 - recall: 0.7512 - auc: 0.8349 - prc: 0.6143 - val_loss: 0.4697 - val_tp: 241.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 76.0000 - val_accuracy: 0.7807 - val_precision: 0.5106 - val_recall: 0.7603 - val_auc: 0.8455 - val_prc: 0.6823
Epoch 185/200
3/3 [==============================] - 0s 17ms/step - loss: 0.4920 - tp: 651.5000 - fp: 817.7500 - tn: 2623.5000 - fn: 207.2500 - accuracy: 0.7629 - precision: 0.4462 - recall: 0.7600 - auc: 0.8399 - prc: 0.6255 - val_loss: 0.4695 - val_tp: 241.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 76.0000 - val_accuracy: 0.7807 - val_precision: 0.5106 - val_recall: 0.7603 - val_auc: 0.8457 - val_prc: 0.6828
Epoch 186/200
3/3 [==============================] - 0s 16ms/step - loss: 0.4930 - tp: 658.5000 - fp: 819.5000 - tn: 2626.2500 - fn: 195.7500 - accuracy: 0.7651 - precision: 0.4476 - recall: 0.7708 - auc: 0.8419 - prc: 0.6243 - val_loss: 0.4674 - val_tp: 241.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 76.0000 - val_accuracy: 0.7807 - val_precision: 0.5106 - val_recall: 0.7603 - val_auc: 0.8457 - val_prc: 0.6827
Epoch 187/200
3/3 [==============================] - 0s 15ms/step - loss: 0.4987 - tp: 631.0000 - fp: 835.2500 - tn: 2611.2500 - fn: 222.5000 - accuracy: 0.7535 - precision: 0.4320 - recall: 0.7391 - auc: 0.8318 - prc: 0.6185 - val_loss: 0.4648 - val_tp: 240.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 77.0000 - val_accuracy: 0.7821 - val_precision: 0.5128 - val_recall: 0.7571 - val_auc: 0.8460 - val_prc: 0.6832
Epoch 188/200
3/3 [==============================] - 0s 16ms/step - loss: 0.4967 - tp: 640.5000 - fp: 803.5000 - tn: 2646.2500 - fn: 209.7500 - accuracy: 0.7641 - precision: 0.4434 - recall: 0.7521 - auc: 0.8374 - prc: 0.6260 - val_loss: 0.4636 - val_tp: 241.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 76.0000 - val_accuracy: 0.7850 - val_precision: 0.5172 - val_recall: 0.7603 - val_auc: 0.8458 - val_prc: 0.6830
Epoch 189/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5040 - tp: 646.7500 - fp: 827.0000 - tn: 2617.5000 - fn: 208.7500 - accuracy: 0.7575 - precision: 0.4363 - recall: 0.7514 - auc: 0.8328 - prc: 0.6179 - val_loss: 0.4636 - val_tp: 240.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 77.0000 - val_accuracy: 0.7821 - val_precision: 0.5128 - val_recall: 0.7571 - val_auc: 0.8455 - val_prc: 0.6831
Epoch 190/200
3/3 [==============================] - 0s 15ms/step - loss: 0.4900 - tp: 648.0000 - fp: 812.5000 - tn: 2639.2500 - fn: 200.2500 - accuracy: 0.7639 - precision: 0.4430 - recall: 0.7679 - auc: 0.8416 - prc: 0.6221 - val_loss: 0.4617 - val_tp: 239.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 78.0000 - val_accuracy: 0.7836 - val_precision: 0.5151 - val_recall: 0.7539 - val_auc: 0.8456 - val_prc: 0.6834
Epoch 191/200
3/3 [==============================] - 0s 15ms/step - loss: 0.5085 - tp: 637.2500 - fp: 812.0000 - tn: 2633.2500 - fn: 217.5000 - accuracy: 0.7594 - precision: 0.4390 - recall: 0.7431 - auc: 0.8293 - prc: 0.6078 - val_loss: 0.4630 - val_tp: 239.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 78.0000 - val_accuracy: 0.7821 - val_precision: 0.5129 - val_recall: 0.7539 - val_auc: 0.8460 - val_prc: 0.6838
Epoch 192/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5003 - tp: 641.5000 - fp: 824.5000 - tn: 2617.0000 - fn: 217.0000 - accuracy: 0.7577 - precision: 0.4396 - recall: 0.7476 - auc: 0.8379 - prc: 0.6069 - val_loss: 0.4635 - val_tp: 239.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 78.0000 - val_accuracy: 0.7807 - val_precision: 0.5107 - val_recall: 0.7539 - val_auc: 0.8462 - val_prc: 0.6841
Epoch 193/200
3/3 [==============================] - 0s 20ms/step - loss: 0.4987 - tp: 655.2500 - fp: 817.0000 - tn: 2634.0000 - fn: 193.7500 - accuracy: 0.7669 - precision: 0.4469 - recall: 0.7737 - auc: 0.8411 - prc: 0.6088 - val_loss: 0.4645 - val_tp: 239.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 78.0000 - val_accuracy: 0.7800 - val_precision: 0.5096 - val_recall: 0.7539 - val_auc: 0.8464 - val_prc: 0.6843
Epoch 194/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5049 - tp: 641.5000 - fp: 841.5000 - tn: 2611.5000 - fn: 205.5000 - accuracy: 0.7545 - precision: 0.4298 - recall: 0.7547 - auc: 0.8299 - prc: 0.5925 - val_loss: 0.4656 - val_tp: 239.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 78.0000 - val_accuracy: 0.7793 - val_precision: 0.5085 - val_recall: 0.7539 - val_auc: 0.8461 - val_prc: 0.6842
Epoch 195/200
3/3 [==============================] - 0s 16ms/step - loss: 0.4909 - tp: 637.2500 - fp: 816.0000 - tn: 2639.2500 - fn: 207.5000 - accuracy: 0.7608 - precision: 0.4348 - recall: 0.7537 - auc: 0.8360 - prc: 0.6338 - val_loss: 0.4664 - val_tp: 241.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 76.0000 - val_accuracy: 0.7800 - val_precision: 0.5095 - val_recall: 0.7603 - val_auc: 0.8462 - val_prc: 0.6839
Epoch 196/200
3/3 [==============================] - 0s 20ms/step - loss: 0.4923 - tp: 639.5000 - fp: 844.7500 - tn: 2617.7500 - fn: 198.0000 - accuracy: 0.7566 - precision: 0.4265 - recall: 0.7646 - auc: 0.8364 - prc: 0.6296 - val_loss: 0.4681 - val_tp: 245.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 72.0000 - val_accuracy: 0.7814 - val_precision: 0.5115 - val_recall: 0.7729 - val_auc: 0.8459 - val_prc: 0.6832
Epoch 197/200
3/3 [==============================] - 0s 17ms/step - loss: 0.4964 - tp: 649.2500 - fp: 834.2500 - tn: 2609.7500 - fn: 206.7500 - accuracy: 0.7566 - precision: 0.4372 - recall: 0.7555 - auc: 0.8367 - prc: 0.6220 - val_loss: 0.4696 - val_tp: 245.0000 - val_fp: 237.0000 - val_tn: 846.0000 - val_fn: 72.0000 - val_accuracy: 0.7793 - val_precision: 0.5083 - val_recall: 0.7729 - val_auc: 0.8459 - val_prc: 0.6836
Epoch 198/200
3/3 [==============================] - 0s 15ms/step - loss: 0.4935 - tp: 643.0000 - fp: 835.0000 - tn: 2627.7500 - fn: 194.2500 - accuracy: 0.7598 - precision: 0.4317 - recall: 0.7706 - auc: 0.8386 - prc: 0.6166 - val_loss: 0.4678 - val_tp: 243.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 74.0000 - val_accuracy: 0.7814 - val_precision: 0.5116 - val_recall: 0.7666 - val_auc: 0.8457 - val_prc: 0.6834
Epoch 199/200
3/3 [==============================] - 0s 15ms/step - loss: 0.4874 - tp: 643.7500 - fp: 830.7500 - tn: 2622.0000 - fn: 203.5000 - accuracy: 0.7608 - precision: 0.4376 - recall: 0.7629 - auc: 0.8436 - prc: 0.6226 - val_loss: 0.4667 - val_tp: 242.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 75.0000 - val_accuracy: 0.7807 - val_precision: 0.5105 - val_recall: 0.7634 - val_auc: 0.8460 - val_prc: 0.6845
Epoch 200/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5136 - tp: 622.7500 - fp: 807.2500 - tn: 2640.7500 - fn: 229.2500 - accuracy: 0.7593 - precision: 0.4357 - recall: 0.7293 - auc: 0.8263 - prc: 0.6013 - val_loss: 0.4678 - val_tp: 241.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 76.0000 - val_accuracy: 0.7807 - val_precision: 0.5106 - val_recall: 0.7603 - val_auc: 0.8459 - val_prc: 0.6842
CPU times: user 18.8 s, sys: 7.08 s, total: 25.9 s
Wall time: 11.7 s


model4.summary()

Model: "sequential_24"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_64 (Dense)             (None, 64)                768       
_________________________________________________________________
dropout_38 (Dropout)         (None, 64)                0         
_________________________________________________________________
dense_65 (Dense)             (None, 24)                1560      
_________________________________________________________________
dropout_39 (Dropout)         (None, 24)                0         
_________________________________________________________________
dense_66 (Dense)             (None, 1)                 25        
=================================================================
Total params: 2,353
Trainable params: 2,353
Non-trainable params: 0
_________________________________________________________________


history_df = pd.DataFrame(history4.history)
history_df['epoch']=history4.epoch
display(history_df)
train_acc = history_df.loc[199,'accuracy']
train_recall = history_df.loc[199,'recall']
train_loss = history_df.loc[199,'loss']


results_df = results_df.loc[:,['model1','model2','model2-tanh']]

results4=model4.evaluate(X_test, y_test.values)

temp_df = pd.DataFrame(results4, index=model3.metrics_names, columns=['model4'])

results_df = pd.merge(results_df, temp_df, left_index=True, right_index=True)

results_df

94/94 [==============================] - 0s 886us/step - loss: 0.4636 - tp: 472.0000 - fp: 546.0000 - tn: 1843.0000 - fn: 139.0000 - accuracy: 0.7717 - precision: 0.4637 - recall: 0.7725 - auc: 0.8550 - prc: 0.6838


plt.figure(figsize=(10,10))
plot_metrics(history4)


y_predict = (model4.predict(X_test) > THRESHOLD).astype('int32')
make_confusion_matrix(model4,y_test, y_predict, cmap='jet')


print(f'Model test loss is: {results_df.loc["loss","model4"]:0.4f}, train loss is {train_loss:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model4"]:0.4f}, train accuracy is {train_acc:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model4"]:0.4f}, train recall is {train_recall:0.4f}')

Model test loss is: 0.4636, train loss is 0.5114
Model test accuracy is: 0.7717, train accuracy is 0.7593
Model test recall is: 0.7725, train recall is 0.7349


import xgboost as xgb
from xgboost import XGBClassifier

from sklearn.model_selection import RandomizedSearchCV
from sklearn.metrics import plot_confusion_matrix, accuracy_score, recall_score, make_scorer

#xgb.config_context()


params= {
        'n_estimators': np.arange(10,150,10),
        'scale_pos_weight': [(neg/pos)], 
        'learning_rate': [0.05,0.1,0.2,0.3], 
        'gamma': np.arange(0,150,10),
        'subsample': [0.5,0.6,0.7,0.8,0.9,1],
        'colsample_bytree': [0.1,0.2,0.3,0.5,0.7,1],
        'max_depth': [3,5,6,8,10,12,15],
        'tree_method': ['hist'], 
        'min_child_weight': [0,3,5,7,8,9,10],
        'colsample_bylevel': [0.5,0.7,1]
    }


%%time
modelx = XGBClassifier()
scorer = metrics.make_scorer(metrics.recall_score)
cvobj = RandomizedSearchCV(estimator=modelx, param_distributions=params, n_iter=50, \
                            scoring=scorer, cv=5, random_state=random_state)


cvobj.fit(X_train, y_train)

CPU times: user 5min 9s, sys: 9.18 s, total: 5min 18s
Wall time: 21.1 s

RandomizedSearchCV(cv=5,
                   estimator=XGBClassifier(base_score=None, booster=None,
                                           colsample_bylevel=None,
                                           colsample_bynode=None,
                                           colsample_bytree=None, gamma=None,
                                           gpu_id=None, importance_type='gain',
                                           interaction_constraints=None,
                                           learning_rate=None,
                                           max_delta_step=None, max_depth=None,
                                           min_child_weight=None, missing=nan,
                                           monotone_constraints=None,
                                           n_estimators=100,...
                                        'gamma': array([  0,  10,  20,  30,  40,  50,  60,  70,  80,  90, 100, 110, 120,
       130, 140]),
                                        'learning_rate': [0.05, 0.1, 0.2, 0.3],
                                        'max_depth': [3, 5, 6, 8, 10, 12, 15],
                                        'min_child_weight': [0, 3, 5, 7, 8, 9,
                                                             10],
                                        'n_estimators': array([ 10,  20,  30,  40,  50,  60,  70,  80,  90, 100, 110, 120, 130,
       140]),
                                        'scale_pos_weight': [3.9091801669121256],
                                        'subsample': [0.5, 0.6, 0.7, 0.8, 0.9,
                                                      1],
                                        'tree_method': ['hist']},
                   random_state=314159, scoring=make_scorer(recall_score))


cvobj.best_estimator_

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, gamma=40, gpu_id=-1,
              importance_type='gain', interaction_constraints='',
              learning_rate=0.2, max_delta_step=0, max_depth=6,
              min_child_weight=3, missing=nan, monotone_constraints='()',
              n_estimators=60, n_jobs=0, num_parallel_tree=1, random_state=0,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=3.9091801669121256,
              subsample=0.6, tree_method='hist', validate_parameters=1,
              verbosity=None)


yypred=cvobj.predict(X_test)


make_confusion_matrix(cvobj, y_test, cmap='Greens')

print(f'accuracy: {accuracy_score(y_test, yypred)}, recall: {recall_score(y_test, yypred)}')

accuracy: 0.792, recall: 0.7430441898527005

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
0	1	15634602	Hargrave	619	France	Female	42	2	0.00	1	1	1	101348.88	1
1	2	15647311	Hill	608	Spain	Female	41	1	83807.86	1	0	1	112542.58	0
2	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1
3	4	15701354	Boni	699	France	Female	39	1	0.00	2	0	0	93826.63	0
4	5	15737888	Mitchell	850	Spain	Female	43	2	125510.82	1	1	1	79084.10	0

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary
Exited
0	651.853196	37.408389	5.033279	72745.296779	1.544267	0.707146	0.554565	99738.391772
1	645.351497	44.837997	4.932744	91108.539337	1.475209	0.699067	0.360825	101465.677531

Gender	Female	Male
Exited
0	0.749285	0.835441
1	0.250715	0.164559

Geography	France	Germany	Spain
Exited
0	0.838452	0.675568	0.833266
1	0.161548	0.324432	0.166734

HasCrCard	0	1
Exited
0	0.791851	0.798157
1	0.208149	0.201843

Pre Work¶

Load Libraries and Define Custom Functions¶

1. Load and Inspect Data¶

2.A EDA - Univariate Analysis¶

2.A (i) Credit Score¶

2.A (ii) Age¶

2.A (iii) Estimated Salary¶

2.A (iv) Balance¶

2.A (v) Tenure¶

2.A (vi) NumOfProducts¶

2.A (vii) HasCrCard¶

2.A (viii) IsActiveMember¶

2.A (ix) Exited (Target Variable)¶

2.A (x) Geography¶

2.A (xi) Gender¶

2.B Bivariate Analysis¶

Examining bivariate relationships - vs. Exited¶

Bivariate vs. Balance¶

3. Data Preprocessing¶

4. Modelling¶

Function and Constants needed for section¶

4.A Base model - only one hidden layer and few nodes¶

4.B Refining the ANN Model - using class weights¶

4.C Using Tanh as activation for the hidden layers¶

4.D Trying more complex model - more hidden layers and more nodes and increasing batch size¶

Final Conclusions and Business Recommendations¶

Appendix: Using XGBoost to check ANN performance¶

	count	mean	std	min	25%	50%	75%	max
RowNumber	10000.0	5.000500e+03	2886.895680	1.00	2500.75	5.000500e+03	7.500250e+03	10000.00
CustomerId	10000.0	1.569094e+07	71936.186123	15565701.00	15628528.25	1.569074e+07	1.575323e+07	15815690.00
CreditScore	10000.0	6.505288e+02	96.653299	350.00	584.00	6.520000e+02	7.180000e+02	850.00
Age	10000.0	3.892180e+01	10.487806	18.00	32.00	3.700000e+01	4.400000e+01	92.00
Tenure	10000.0	5.012800e+00	2.892174	0.00	3.00	5.000000e+00	7.000000e+00	10.00
Balance	10000.0	7.648589e+04	62397.405202	0.00	0.00	9.719854e+04	1.276442e+05	250898.09
NumOfProducts	10000.0	1.530200e+00	0.581654	1.00	1.00	1.000000e+00	2.000000e+00	4.00
HasCrCard	10000.0	7.055000e-01	0.455840	0.00	0.00	1.000000e+00	1.000000e+00	1.00
IsActiveMember	10000.0	5.151000e-01	0.499797	0.00	0.00	1.000000e+00	1.000000e+00	1.00
EstimatedSalary	10000.0	1.000902e+05	57510.492818	11.58	51002.11	1.001939e+05	1.493882e+05	199992.48
Exited	10000.0	2.037000e-01	0.402769	0.00	0.00	0.000000e+00	0.000000e+00	1.00

	count	unique	top	freq
Surname	10000	2932	Smith	32
Geography	10000	3	France	5014
Gender	10000	2	Male	5457

	n_uniques	col_types	isnumeric_column	probably_categorical
CreditScore	460	int64	True	False
Age	70	int64	True	False
Tenure	11	int64	True	True
NumOfProducts	4	int64	True	True
HasCrCard	2	int64	True	True
IsActiveMember	2	int64	True	True
Exited	2	int64	True	True
Balance	6382	float64	True	False
EstimatedSalary	9999	float64	True	False
Geography	3	object	False	True
Gender	2	object	False	True

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary
Exited
0	653	36	5	92072.68	2	1	1	99645.04
1	646	45	5	109349.29	1	1	0	102460.84

NumOfProducts	1	2	3	4
Exited
0	0.722856	0.924183	0.172932	0.0
1	0.277144	0.075817	0.827068	1.0

Tenure	0	1	2	3	4	5	6	7	8	9	10
Exited
0	0.769976	0.775845	0.808206	0.7889	0.794742	0.793478	0.797311	0.827821	0.807805	0.783537	0.793878
1	0.230024	0.224155	0.191794	0.2111	0.205258	0.206522	0.202689	0.172179	0.192195	0.216463	0.206122

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Geography_Germany	Geography_Spain	Gender_Male
2441	735	29	10	0.00	2	1	1	95025.27	0	1	1
2786	511	40	9	124401.60	1	1	0	198814.24	1	0	0
2375	815	39	6	0.00	1	1	1	85167.88	0	1	0
3566	746	25	3	104833.79	1	0	0	71911.30	0	1	0
7616	610	27	4	87262.40	2	1	0	182720.07	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...
2513	666	39	10	0.00	2	1	0	102999.33	0	0	1
8474	721	33	4	72535.45	1	1	1	103931.49	0	1	0
4528	714	31	6	152926.60	1	1	1	50899.91	0	1	0
1732	735	49	5	121973.28	1	1	0	148804.36	0	0	1
5914	754	27	7	117578.35	2	0	1	87908.01	1	0	1

	count	mean	std	min	25%	50%	75%	max
CreditScore	7000.0	-0.011733	0.719086	-2.253731	-0.514925	0.000000e+00	0.485075	1.477612
Age	7000.0	0.168060	0.881617	-1.583333	-0.416667	0.000000e+00	0.583333	4.583333
Tenure	7000.0	-0.001743	0.578801	-1.000000	-0.600000	0.000000e+00	0.400000	1.000000
Balance	7000.0	-0.164601	0.490244	-0.761774	-0.761774	-5.722110e-17	0.238226	1.211395
NumOfProducts	7000.0	0.526571	0.579087	0.000000	0.000000	0.000000e+00	1.000000	3.000000
HasCrCard	7000.0	-0.293000	0.455171	-1.000000	-1.000000	0.000000e+00	0.000000	0.000000
IsActiveMember	7000.0	-0.480714	0.499664	-1.000000	-1.000000	0.000000e+00	0.000000	0.000000
EstimatedSalary	7000.0	0.001752	0.589707	-1.028401	-0.494425	7.470153e-17	0.505575	1.024988
Geography_Germany	7000.0	0.251571	0.433947	0.000000	0.000000	0.000000e+00	1.000000	1.000000
Geography_Spain	7000.0	0.251571	0.433947	0.000000	0.000000	0.000000e+00	1.000000	1.000000
Gender_Male	7000.0	-0.455571	0.498058	-1.000000	-1.000000	0.000000e+00	0.000000	0.000000

	count	mean	std	min	25%	50%	75%	max
CreditScore	3000.0	-0.009219	0.726535	-2.253731	-0.507463	-0.007463	0.501866	1.477612
Age	3000.0	0.141694	0.855769	-1.583333	-0.416667	0.000000	0.500000	4.583333
Tenure	3000.0	0.012600	0.577552	-1.000000	-0.400000	0.000000	0.600000	1.000000
Balance	3000.0	-0.150121	0.491760	-0.761774	-0.761774	0.007951	0.250175	1.113007
NumOfProducts	3000.0	0.538667	0.587611	0.000000	0.000000	0.000000	1.000000	3.000000
HasCrCard	3000.0	-0.298000	0.457456	-1.000000	-1.000000	0.000000	0.000000	0.000000
IsActiveMember	3000.0	-0.494667	0.500055	-1.000000	-1.000000	0.000000	0.000000	0.000000
EstimatedSalary	3000.0	-0.006758	0.592448	-1.027595	-0.520785	0.002163	0.504898	1.024338
Geography_Germany	3000.0	0.249333	0.432699	0.000000	0.000000	0.000000	0.000000	1.000000
Geography_Spain	3000.0	0.238667	0.426340	0.000000	0.000000	0.000000	0.000000	1.000000
Gender_Male	3000.0	-0.451333	0.497709	-1.000000	-1.000000	0.000000	0.000000	0.000000

	loss	tp	fp	tn	fn	accuracy	precision	recall	auc	prc	...	val_tp	val_fp	val_tn	val_fn	val_accuracy	val_precision	val_recall	val_auc	val_prc	epoch
0	0.528808	1.0	2.0	4489.0	1108.0	0.801786	0.333333	0.000902	0.476185	0.201644	...	0.0	0.0	1083.0	317.0	0.773571	0.000000	0.000000	0.553019	0.301213	0
1	0.498302	0.0	1.0	4490.0	1109.0	0.801786	0.000000	0.000000	0.583951	0.263688	...	1.0	1.0	1082.0	316.0	0.773571	0.500000	0.003155	0.640923	0.345919	1
2	0.475593	7.0	8.0	4483.0	1102.0	0.801786	0.466667	0.006312	0.665710	0.333606	...	6.0	9.0	1074.0	311.0	0.771429	0.400000	0.018927	0.690627	0.387364	2
3	0.457817	37.0	24.0	4467.0	1072.0	0.804286	0.606557	0.033363	0.709794	0.395459	...	17.0	16.0	1067.0	300.0	0.774286	0.515152	0.053628	0.716865	0.419273	3
4	0.444412	89.0	53.0	4438.0	1020.0	0.808393	0.626761	0.080252	0.734889	0.437439	...	32.0	21.0	1062.0	285.0	0.781429	0.603774	0.100946	0.733200	0.450563	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
95	0.323197	524.0	149.0	4342.0	585.0	0.868929	0.778603	0.472498	0.871577	0.709965	...	145.0	49.0	1034.0	172.0	0.842143	0.747423	0.457413	0.850866	0.695210	95
96	0.323193	537.0	169.0	4322.0	572.0	0.867679	0.760623	0.484220	0.871391	0.709899	...	139.0	42.0	1041.0	178.0	0.842857	0.767956	0.438486	0.850666	0.695150	96
97	0.323068	534.0	163.0	4328.0	575.0	0.868214	0.766141	0.481515	0.871662	0.710155	...	141.0	43.0	1040.0	176.0	0.843571	0.766304	0.444795	0.850777	0.695114	97
98	0.323003	529.0	158.0	4333.0	580.0	0.868214	0.770015	0.477006	0.871430	0.710129	...	143.0	49.0	1034.0	174.0	0.840714	0.744792	0.451104	0.850922	0.694822	98
99	0.322963	536.0	167.0	4324.0	573.0	0.867857	0.762447	0.483318	0.871644	0.710267	...	143.0	48.0	1035.0	174.0	0.841429	0.748691	0.451104	0.850848	0.694686	99

IsActiveMember	0	1
Exited
0	0.731491	0.857309
1	0.268509	0.142691

	model1
loss	0.347151
tp	295.000000
fp	108.000000
tn	2281.000000
fn	316.000000
accuracy	0.858667
precision	0.732010
recall	0.482815
auc	0.851066
prc	0.686293

	loss	tp	fp	tn	fn	accuracy	precision	recall	auc	prc	...	val_tp	val_fp	val_tn	val_fn	val_accuracy	val_precision	val_recall	val_auc	val_prc	epoch
0	0.768797	713.0	1873.0	5007.0	1007.0	0.665116	0.275715	0.414535	0.633278	0.357970	...	139.0	381.0	702.0	178.0	0.600714	0.267308	0.438486	0.542718	0.260557	0
1	0.695894	596.0	1926.0	2565.0	513.0	0.564464	0.236320	0.537421	0.571988	0.260424	...	182.0	386.0	697.0	135.0	0.627857	0.320423	0.574133	0.638912	0.352243	1
2	0.668457	641.0	1831.0	2660.0	468.0	0.589464	0.259304	0.577998	0.621545	0.308399	...	202.0	378.0	705.0	115.0	0.647857	0.348276	0.637224	0.697757	0.409228	2
3	0.644562	704.0	1762.0	2729.0	405.0	0.613036	0.285483	0.634806	0.666937	0.347349	...	215.0	358.0	725.0	102.0	0.671429	0.375218	0.678233	0.729346	0.431829	3
4	0.639620	702.0	1671.0	2820.0	407.0	0.628929	0.295828	0.633003	0.677914	0.355460	...	218.0	345.0	738.0	99.0	0.682857	0.387211	0.687697	0.743103	0.440434	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
195	0.519189	754.0	863.0	3628.0	355.0	0.782500	0.466296	0.679892	0.817705	0.589741	...	220.0	195.0	888.0	97.0	0.791429	0.530120	0.694006	0.843840	0.681117	195
196	0.501904	780.0	876.0	3615.0	329.0	0.784821	0.471014	0.703336	0.834418	0.601390	...	218.0	190.0	893.0	99.0	0.793571	0.534314	0.687697	0.844939	0.683199	196
197	0.500092	764.0	833.0	3658.0	345.0	0.789643	0.478397	0.688909	0.832839	0.609324	...	221.0	189.0	894.0	96.0	0.796429	0.539024	0.697161	0.845220	0.684418	197
198	0.502370	779.0	883.0	3608.0	330.0	0.783393	0.468712	0.702435	0.833352	0.603129	...	222.0	192.0	891.0	95.0	0.795000	0.536232	0.700315	0.845695	0.684913	198
199	0.503482	784.0	884.0	3607.0	325.0	0.784107	0.470024	0.706943	0.832640	0.591892	...	220.0	197.0	886.0	97.0	0.790000	0.527578	0.694006	0.845212	0.685141	199

	model1	model2
loss	0.347151	0.471099
tp	295.000000	442.000000
fp	108.000000	451.000000
tn	2281.000000	1938.000000
fn	316.000000	169.000000
accuracy	0.858667	0.793333
precision	0.732010	0.494961
recall	0.482815	0.723404
auc	0.851066	0.849314
prc	0.686293	0.671011

	loss	tp	fp	tn	fn	accuracy	precision	recall	auc	prc	...	val_tp	val_fp	val_tn	val_fn	val_accuracy	val_precision	val_recall	val_auc	val_prc	epoch
0	0.778988	1326.0	4096.0	2784.0	394.0	0.477907	0.244559	0.770930	0.644444	0.363573	...	310.0	1074.0	9.0	7.0	0.227857	0.223988	0.977918	0.517352	0.229215	0
1	0.753992	873.0	3465.0	1026.0	236.0	0.339107	0.201245	0.787196	0.508031	0.197948	...	307.0	1020.0	63.0	10.0	0.264286	0.231349	0.968454	0.571611	0.258331	1
2	0.739489	813.0	3245.0	1246.0	296.0	0.367679	0.200345	0.733093	0.514896	0.207458	...	300.0	943.0	140.0	17.0	0.314286	0.241352	0.946372	0.612984	0.287669	2
3	0.712113	852.0	3158.0	1333.0	257.0	0.390179	0.212469	0.768260	0.558319	0.232937	...	295.0	849.0	234.0	22.0	0.377857	0.257867	0.930599	0.642534	0.313610	3
4	0.701110	825.0	2998.0	1493.0	284.0	0.413929	0.215799	0.743913	0.563521	0.234551	...	290.0	785.0	298.0	27.0	0.420000	0.269767	0.914827	0.665509	0.337811	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
195	0.499596	846.0	1089.0	3402.0	263.0	0.758571	0.437209	0.762849	0.836383	0.632389	...	245.0	234.0	849.0	72.0	0.781429	0.511482	0.772871	0.845893	0.683245	195
196	0.490138	846.0	1082.0	3409.0	263.0	0.759821	0.438797	0.762849	0.840116	0.625571	...	245.0	237.0	846.0	72.0	0.779286	0.508299	0.772871	0.845911	0.683556	196
197	0.497858	847.0	1073.0	3418.0	262.0	0.761607	0.441146	0.763751	0.838953	0.626003	...	243.0	232.0	851.0	74.0	0.781429	0.511579	0.766562	0.845671	0.683391	197
198	0.494574	835.0	1089.0	3402.0	274.0	0.756607	0.433992	0.752931	0.838186	0.617359	...	242.0	232.0	851.0	75.0	0.780714	0.510549	0.763407	0.845968	0.684454	198
199	0.511383	815.0	1054.0	3437.0	294.0	0.759286	0.436062	0.734896	0.827745	0.599253	...	241.0	231.0	852.0	76.0	0.780714	0.510593	0.760252	0.845880	0.684150	199